[PATCH v1 00/11] Introduce error threshold to drm_ras

[PATCH v1 00/11] Introduce error threshold to drm_ras

[Raag Jadav]

This series reuses some pieces of [1] and [2] and introduces error
threshold to drm_ras infrastructure. This allows user to get and set
the threshold value of a specific error.

Detailed description in commit message and documentation.

[1] https://patchwork.freedesktop.org/series/164393/
[2] https://patchwork.freedesktop.org/series/160184/

Raag Jadav (9):
  drm/ras: Update counter helpers with counter naming
  drm/ras: Introduce get-error-threshold
  drm/ras: Introduce set-error-threshold
  drm/xe/sysctrl: Add system controller interrupt handler
  drm/xe/sysctrl: Add system controller event support
  drm/xe/ras: Introduce correctable error handling
  drm/xe/ras: Get error threshold support
  drm/xe/ras: Set error threshold support
  drm/xe/drm_ras: Wire up error threshold callbacks

Riana Tauro (2):
  drm/xe/uapi: Add additional error components to XE drm_ras
  drm/xe/ras: Add flag for Xe RAS

 Documentation/gpu/drm-ras.rst                 |  17 ++
 Documentation/netlink/specs/drm_ras.yaml      |  49 +++++
 drivers/gpu/drm/drm_ras.c                     | 165 +++++++++++++-
 drivers/gpu/drm/drm_ras_nl.c                  |  27 +++
 drivers/gpu/drm/drm_ras_nl.h                  |   4 +
 drivers/gpu/drm/xe/Makefile                   |   2 +
 drivers/gpu/drm/xe/regs/xe_irq_regs.h         |   1 +
 drivers/gpu/drm/xe/xe_device_types.h          |   2 +
 drivers/gpu/drm/xe/xe_drm_ras.c               |  29 ++-
 drivers/gpu/drm/xe/xe_hw_error.c              |   2 +-
 drivers/gpu/drm/xe/xe_irq.c                   |   2 +
 drivers/gpu/drm/xe/xe_pci.c                   |   3 +
 drivers/gpu/drm/xe/xe_pci_types.h             |   1 +
 drivers/gpu/drm/xe/xe_ras.c                   | 207 ++++++++++++++++++
 drivers/gpu/drm/xe/xe_ras.h                   |  19 ++
 drivers/gpu/drm/xe/xe_ras_types.h             | 123 +++++++++++
 drivers/gpu/drm/xe/xe_sysctrl.c               |  46 +++-
 drivers/gpu/drm/xe/xe_sysctrl.h               |   2 +
 drivers/gpu/drm/xe/xe_sysctrl_event.c         |  87 ++++++++
 drivers/gpu/drm/xe/xe_sysctrl_event_types.h   |  57 +++++
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |  22 ++
 drivers/gpu/drm/xe/xe_sysctrl_types.h         |   7 +
 include/drm/drm_ras.h                         |  27 +++
 include/uapi/drm/drm_ras.h                    |  12 +
 include/uapi/drm/xe_drm.h                     |  11 +-
 25 files changed, 906 insertions(+), 18 deletions(-)
 create mode 100644 drivers/gpu/drm/xe/xe_ras.c
 create mode 100644 drivers/gpu/drm/xe/xe_ras.h
 create mode 100644 drivers/gpu/drm/xe/xe_ras_types.h
 create mode 100644 drivers/gpu/drm/xe/xe_sysctrl_event.c
 create mode 100644 drivers/gpu/drm/xe/xe_sysctrl_event_types.h

-- 
2.43.0

[PATCH v1 01/11] drm/ras: Update counter helpers with counter naming

[Raag Jadav]

Counter helpers deal with counter values. Use the appropriate naming to
match with their functionality.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 drivers/gpu/drm/drm_ras.c | 14 +++++++-------
 1 file changed, 7 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
index b2fa5ab86d87..1f7435d60f11 100644
--- a/drivers/gpu/drm/drm_ras.c
+++ b/drivers/gpu/drm/drm_ras.c
@@ -162,8 +162,8 @@ static int get_node_error_counter(u32 node_id, u32 error_id,
 	return node->query_error_counter(node, error_id, name, value);
 }
 
-static int msg_reply_value(struct sk_buff *msg, u32 error_id,
-			   const char *error_name, u32 value)
+static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
+				   const char *error_name, u32 value)
 {
 	int ret;
 
@@ -180,8 +180,8 @@ static int msg_reply_value(struct sk_buff *msg, u32 error_id,
 			   value);
 }
 
-static int doit_reply_value(struct genl_info *info, u32 node_id,
-			    u32 error_id)
+static int doit_reply_counter_value(struct genl_info *info, u32 node_id,
+				    u32 error_id)
 {
 	struct sk_buff *msg;
 	struct nlattr *hdr;
@@ -204,7 +204,7 @@ static int doit_reply_value(struct genl_info *info, u32 node_id,
 	if (ret)
 		return ret;
 
-	ret = msg_reply_value(msg, error_id, error_name, value);
+	ret = msg_reply_counter_value(msg, error_id, error_name, value);
 	if (ret) {
 		genlmsg_cancel(msg, hdr);
 		nlmsg_free(msg);
@@ -272,7 +272,7 @@ int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
 			break;
 		}
 
-		ret = msg_reply_value(skb, error_id, error_name, value);
+		ret = msg_reply_counter_value(skb, error_id, error_name, value);
 		if (ret) {
 			genlmsg_cancel(skb, hdr);
 			break;
@@ -311,7 +311,7 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
 	node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID]);
 	error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_COUNTER_ATTRS_ERROR_ID]);
 
-	return doit_reply_value(info, node_id, error_id);
+	return doit_reply_counter_value(info, node_id, error_id);
 }
 
 /**
-- 
2.43.0

[PATCH v1 02/11] drm/ras: Introduce get-error-threshold

[Raag Jadav]

Add get-error-threshold command support which allows querying threshold
value of the error. Threshold in RAS context means the number of errors
the hardware is expected to accumulate before it raises them to software.
This is to have a fine grained control over error notifications that are
raised by the hardware.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 Documentation/gpu/drm-ras.rst            |   8 ++
 Documentation/netlink/specs/drm_ras.yaml |  37 ++++++++
 drivers/gpu/drm/drm_ras.c                | 103 +++++++++++++++++++++++
 drivers/gpu/drm/drm_ras_nl.c             |  13 +++
 drivers/gpu/drm/drm_ras_nl.h             |   2 +
 include/drm/drm_ras.h                    |  14 +++
 include/uapi/drm/drm_ras.h               |  11 +++
 7 files changed, 188 insertions(+)

diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
index 70b246a78fc8..6443dfd1677f 100644
--- a/Documentation/gpu/drm-ras.rst
+++ b/Documentation/gpu/drm-ras.rst
@@ -52,6 +52,8 @@ User space tools can:
   as a parameter.
 * Query specific error counter values with the ``get-error-counter`` command, using both
   ``node-id`` and ``error-id`` as parameters.
+* Query specific error threshold value with the ``get-error-threshold`` command, using both
+  ``node-id`` and ``error-id`` as parameters.
 
 YAML-based Interface
 --------------------
@@ -101,3 +103,9 @@ Example: Query an error counter for a given node
     sudo ynl --family drm_ras --do get-error-counter --json '{"node-id":0, "error-id":1}'
     {'error-id': 1, 'error-name': 'error_name1', 'error-value': 0}
 
+Example: Query threshold value of a given error
+
+.. code-block:: bash
+
+    sudo ynl --family drm_ras --do get-error-threshold --json '{"node-id":0, "error-id":1}'
+    {'error-id': 1, 'error-name': 'error_name1', 'error-threshold': 0}
diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
index 79af25dac3c5..95a939fb987d 100644
--- a/Documentation/netlink/specs/drm_ras.yaml
+++ b/Documentation/netlink/specs/drm_ras.yaml
@@ -69,6 +69,25 @@ attribute-sets:
         name: error-value
         type: u32
         doc: Current value of the requested error counter.
+  -
+    name: error-threshold-attrs
+    attributes:
+      -
+        name: node-id
+        type: u32
+        doc: Node ID targeted by this operation.
+      -
+        name: error-id
+        type: u32
+        doc: Unique identifier for a specific error within the node.
+      -
+        name: error-name
+        type: string
+        doc: Name of the error.
+      -
+        name: error-threshold
+        type: u32
+        doc: Threshold value of the error.
 
 operations:
   list:
@@ -113,3 +132,21 @@ operations:
             - node-id
         reply:
           attributes: *errorinfo
+    -
+      name: get-error-threshold
+      doc: >-
+           Retrieve threshold value of the error.
+           The response includes the id, the name, and current threshold
+           value of the error.
+      attribute-set: error-threshold-attrs
+      flags: [admin-perm]
+      do:
+        request:
+          attributes:
+            - node-id
+            - error-id
+        reply:
+          attributes:
+            - error-id
+            - error-name
+            - error-threshold
diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
index 1f7435d60f11..d2d853d5d69c 100644
--- a/drivers/gpu/drm/drm_ras.c
+++ b/drivers/gpu/drm/drm_ras.c
@@ -37,6 +37,10 @@
  *    Returns all counters of a node if only Node ID is provided or specific
  *    error counters.
  *
+ * 3. GET_ERROR_THRESHOLD: Query threshold value of the error.
+ *    Userspace must provide Node ID and Error ID.
+ *    Returns the threshold value of a specific error.
+ *
  * Node registration:
  *
  * - drm_ras_node_register(): Registers a new node and assigns
@@ -66,6 +70,8 @@
  *   operation, fetching all counters from a specific node.
  * - drm_ras_nl_get_error_counter_doit(): Implements the GET_ERROR_COUNTER doit
  *   operation, fetching a counter value from a specific node.
+ * - drm_ras_nl_get_error_threshold_doit(): Implements the GET_ERROR_THRESHOLD doit
+ *   operation, fetching the threshold value of a specific error.
  */
 
 static DEFINE_XARRAY_ALLOC(drm_ras_xa);
@@ -162,6 +168,22 @@ static int get_node_error_counter(u32 node_id, u32 error_id,
 	return node->query_error_counter(node, error_id, name, value);
 }
 
+static int get_node_error_threshold(u32 node_id, u32 error_id,
+				    const char **name, u32 *value)
+{
+	struct drm_ras_node *node;
+
+	node = xa_load(&drm_ras_xa, node_id);
+	if (!node || !node->query_error_threshold)
+		return -ENOENT;
+
+	if (error_id < node->error_counter_range.first ||
+	    error_id > node->error_counter_range.last)
+		return -EINVAL;
+
+	return node->query_error_threshold(node, error_id, name, value);
+}
+
 static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
 				   const char *error_name, u32 value)
 {
@@ -180,6 +202,24 @@ static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
 			   value);
 }
 
+static int msg_reply_threshold_value(struct sk_buff *msg, u32 error_id,
+				     const char *error_name, u32 value)
+{
+	int ret;
+
+	ret = nla_put_u32(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID, error_id);
+	if (ret)
+		return ret;
+
+	ret = nla_put_string(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_NAME,
+			     error_name);
+	if (ret)
+		return ret;
+
+	return nla_put_u32(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD,
+			   value);
+}
+
 static int doit_reply_counter_value(struct genl_info *info, u32 node_id,
 				    u32 error_id)
 {
@@ -216,6 +256,42 @@ static int doit_reply_counter_value(struct genl_info *info, u32 node_id,
 	return genlmsg_reply(msg, info);
 }
 
+static int doit_reply_threshold_value(struct genl_info *info, u32 node_id,
+				      u32 error_id)
+{
+	struct sk_buff *msg;
+	struct nlattr *hdr;
+	const char *error_name;
+	u32 value;
+	int ret;
+
+	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
+	if (!msg)
+		return -ENOMEM;
+
+	hdr = genlmsg_iput(msg, info);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return -EMSGSIZE;
+	}
+
+	ret = get_node_error_threshold(node_id, error_id,
+				       &error_name, &value);
+	if (ret)
+		return ret;
+
+	ret = msg_reply_threshold_value(msg, error_id, error_name, value);
+	if (ret) {
+		genlmsg_cancel(msg, hdr);
+		nlmsg_free(msg);
+		return ret;
+	}
+
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_reply(msg, info);
+}
+
 /**
  * drm_ras_nl_get_error_counter_dumpit() - Dump all Error Counters
  * @skb: Netlink message buffer
@@ -314,6 +390,33 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
 	return doit_reply_counter_value(info, node_id, error_id);
 }
 
+/**
+ * drm_ras_nl_get_error_threshold_doit() - Query threshold value of the error
+ * @skb: Netlink message buffer
+ * @info: Generic Netlink info containing attributes of the request
+ *
+ * Extracts the node ID and error ID from the netlink attributes and
+ * retrieves the current threshold of the corresponding error. Sends the
+ * result back to the requesting user via the standard Genl reply.
+ *
+ * Return: 0 on success, or negative errno on failure.
+ */
+int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
+				      struct genl_info *info)
+{
+	u32 node_id, error_id;
+
+	if (!info->attrs ||
+	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID) ||
+	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID))
+		return -EINVAL;
+
+	node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID]);
+	error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID]);
+
+	return doit_reply_threshold_value(info, node_id, error_id);
+}
+
 /**
  * drm_ras_node_register() - Register a new RAS node
  * @node: Node structure to register
diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c
index 16803d0c4a44..48e231734f4d 100644
--- a/drivers/gpu/drm/drm_ras_nl.c
+++ b/drivers/gpu/drm/drm_ras_nl.c
@@ -22,6 +22,12 @@ static const struct nla_policy drm_ras_get_error_counter_dump_nl_policy[DRM_RAS_
 	[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID] = { .type = NLA_U32, },
 };
 
+/* DRM_RAS_CMD_GET_ERROR_THRESHOLD - do */
+static const struct nla_policy drm_ras_get_error_threshold_nl_policy[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID + 1] = {
+	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID] = { .type = NLA_U32, },
+	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID] = { .type = NLA_U32, },
+};
+
 /* Ops table for drm_ras */
 static const struct genl_split_ops drm_ras_nl_ops[] = {
 	{
@@ -43,6 +49,13 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
 		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
 	},
+	{
+		.cmd		= DRM_RAS_CMD_GET_ERROR_THRESHOLD,
+		.doit		= drm_ras_nl_get_error_threshold_doit,
+		.policy		= drm_ras_get_error_threshold_nl_policy,
+		.maxattr	= DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 struct genl_family drm_ras_nl_family __ro_after_init = {
diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h
index 06ccd9342773..540fe22e2312 100644
--- a/drivers/gpu/drm/drm_ras_nl.h
+++ b/drivers/gpu/drm/drm_ras_nl.h
@@ -18,6 +18,8 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
 				      struct genl_info *info);
 int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
 					struct netlink_callback *cb);
+int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
+					struct genl_info *info);
 
 extern struct genl_family drm_ras_nl_family;
 
diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
index 5d50209e51db..50cee70bd065 100644
--- a/include/drm/drm_ras.h
+++ b/include/drm/drm_ras.h
@@ -57,6 +57,20 @@ struct drm_ras_node {
 	 */
 	int (*query_error_counter)(struct drm_ras_node *node, u32 error_id,
 				   const char **name, u32 *val);
+	/**
+	 * @query_error_threshold:
+	 *
+	 * This callback is used by drm-ras to query threshold value of a
+	 * specific error.
+	 *
+	 * Driver should expect query_error_threshold() to be called with
+	 * error_id from `error_counter_range.first` to
+	 * `error_counter_range.last`.
+	 *
+	 * Returns: 0 on success, negative error code on failure.
+	 */
+	int (*query_error_threshold)(struct drm_ras_node *node, u32 error_id,
+				     const char **name, u32 *val);
 
 	/** @priv: Driver private data */
 	void *priv;
diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
index 5f40fa5b869d..49c5ca497d73 100644
--- a/include/uapi/drm/drm_ras.h
+++ b/include/uapi/drm/drm_ras.h
@@ -38,9 +38,20 @@ enum {
 	DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1)
 };
 
+enum {
+	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID = 1,
+	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID,
+	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_NAME,
+	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD,
+
+	__DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX,
+	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX = (__DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX - 1)
+};
+
 enum {
 	DRM_RAS_CMD_LIST_NODES = 1,
 	DRM_RAS_CMD_GET_ERROR_COUNTER,
+	DRM_RAS_CMD_GET_ERROR_THRESHOLD,
 
 	__DRM_RAS_CMD_MAX,
 	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)
-- 
2.43.0

[PATCH v1 03/11] drm/ras: Introduce set-error-threshold

[Raag Jadav]

Add set-error-threshold command support which allows setting threshold
value of the error. Threshold in RAS context means the number of errors
the hardware is expected to accumulate before it raises them to software.
This is to have a fine grained control over error notifications that are
raised by the hardware.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 Documentation/gpu/drm-ras.rst            |  9 +++++
 Documentation/netlink/specs/drm_ras.yaml | 12 ++++++
 drivers/gpu/drm/drm_ras.c                | 48 ++++++++++++++++++++++++
 drivers/gpu/drm/drm_ras_nl.c             | 14 +++++++
 drivers/gpu/drm/drm_ras_nl.h             |  2 +
 include/drm/drm_ras.h                    | 13 +++++++
 include/uapi/drm/drm_ras.h               |  1 +
 7 files changed, 99 insertions(+)

diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
index 6443dfd1677f..a819aa150604 100644
--- a/Documentation/gpu/drm-ras.rst
+++ b/Documentation/gpu/drm-ras.rst
@@ -54,6 +54,8 @@ User space tools can:
   ``node-id`` and ``error-id`` as parameters.
 * Query specific error threshold value with the ``get-error-threshold`` command, using both
   ``node-id`` and ``error-id`` as parameters.
+* Set specific error threshold value with the ``set-error-threshold`` command, using
+  ``node-id``, ``error-id`` and ``error-threshold`` as parameters.
 
 YAML-based Interface
 --------------------
@@ -109,3 +111,10 @@ Example: Query threshold value of a given error
 
     sudo ynl --family drm_ras --do get-error-threshold --json '{"node-id":0, "error-id":1}'
     {'error-id': 1, 'error-name': 'error_name1', 'error-threshold': 0}
+
+Example: Set threshold value of a given error
+
+.. code-block:: bash
+
+    sudo ynl --family drm_ras --do set-error-threshold --json '{"node-id":0, "error-id":1, "error-threshold":8}'
+    None
diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
index 95a939fb987d..09824309cdff 100644
--- a/Documentation/netlink/specs/drm_ras.yaml
+++ b/Documentation/netlink/specs/drm_ras.yaml
@@ -150,3 +150,15 @@ operations:
             - error-id
             - error-name
             - error-threshold
+    -
+      name: set-error-threshold
+      doc: >-
+           Set threshold value of the error.
+      attribute-set: error-threshold-attrs
+      flags: [admin-perm]
+      do:
+        request:
+          attributes:
+            - node-id
+            - error-id
+            - error-threshold
diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
index d2d853d5d69c..e4ff6d87f824 100644
--- a/drivers/gpu/drm/drm_ras.c
+++ b/drivers/gpu/drm/drm_ras.c
@@ -41,6 +41,9 @@
  *    Userspace must provide Node ID and Error ID.
  *    Returns the threshold value of a specific error.
  *
+ * 4. SET_ERROR_THRESHOLD: Set threshold value of the error.
+ *    Userspace must provide Node ID, Error ID and Threshold value to be set.
+ *
  * Node registration:
  *
  * - drm_ras_node_register(): Registers a new node and assigns
@@ -72,6 +75,8 @@
  *   operation, fetching a counter value from a specific node.
  * - drm_ras_nl_get_error_threshold_doit(): Implements the GET_ERROR_THRESHOLD doit
  *   operation, fetching the threshold value of a specific error.
+ * - drm_ras_nl_set_error_threshold_doit(): Implements the SET_ERROR_THRESHOLD doit
+ *   operation, setting the threshold value of a specific error.
  */
 
 static DEFINE_XARRAY_ALLOC(drm_ras_xa);
@@ -184,6 +189,21 @@ static int get_node_error_threshold(u32 node_id, u32 error_id,
 	return node->query_error_threshold(node, error_id, name, value);
 }
 
+static int set_node_error_threshold(u32 node_id, u32 error_id, u32 value)
+{
+	struct drm_ras_node *node;
+
+	node = xa_load(&drm_ras_xa, node_id);
+	if (!node || !node->set_error_threshold)
+		return -ENOENT;
+
+	if (error_id < node->error_counter_range.first ||
+	    error_id > node->error_counter_range.last)
+		return -EINVAL;
+
+	return node->set_error_threshold(node, error_id, value);
+}
+
 static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
 				   const char *error_name, u32 value)
 {
@@ -417,6 +437,34 @@ int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
 	return doit_reply_threshold_value(info, node_id, error_id);
 }
 
+/**
+ * drm_ras_nl_set_error_threshold_doit() - Set threshold value of the error
+ * @skb: Netlink message buffer
+ * @info: Generic Netlink info containing attributes of the request
+ *
+ * Extracts the node ID, error ID and threshold value from the netlink attributes
+ * and sets the threshold of the corresponding error.
+ *
+ * Return: 0 on success, or negative errno on failure.
+ */
+int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb,
+				      struct genl_info *info)
+{
+	u32 node_id, error_id, value;
+
+	if (!info->attrs ||
+	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID) ||
+	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID) ||
+	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD))
+		return -EINVAL;
+
+	node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID]);
+	error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID]);
+	value = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD]);
+
+	return set_node_error_threshold(node_id, error_id, value);
+}
+
 /**
  * drm_ras_node_register() - Register a new RAS node
  * @node: Node structure to register
diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c
index 48e231734f4d..8b202d773dac 100644
--- a/drivers/gpu/drm/drm_ras_nl.c
+++ b/drivers/gpu/drm/drm_ras_nl.c
@@ -28,6 +28,13 @@ static const struct nla_policy drm_ras_get_error_threshold_nl_policy[DRM_RAS_A_E
 	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID] = { .type = NLA_U32, },
 };
 
+/* DRM_RAS_CMD_SET_ERROR_THRESHOLD - do */
+static const struct nla_policy drm_ras_set_error_threshold_nl_policy[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD + 1] = {
+	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID] = { .type = NLA_U32, },
+	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID] = { .type = NLA_U32, },
+	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD] = { .type = NLA_U32, },
+};
+
 /* Ops table for drm_ras */
 static const struct genl_split_ops drm_ras_nl_ops[] = {
 	{
@@ -56,6 +63,13 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
 		.maxattr	= DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID,
 		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
 	},
+	{
+		.cmd		= DRM_RAS_CMD_SET_ERROR_THRESHOLD,
+		.doit		= drm_ras_nl_set_error_threshold_doit,
+		.policy		= drm_ras_set_error_threshold_nl_policy,
+		.maxattr	= DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD,
+		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
+	},
 };
 
 struct genl_family drm_ras_nl_family __ro_after_init = {
diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h
index 540fe22e2312..9db7f5d00201 100644
--- a/drivers/gpu/drm/drm_ras_nl.h
+++ b/drivers/gpu/drm/drm_ras_nl.h
@@ -20,6 +20,8 @@ int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
 					struct netlink_callback *cb);
 int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
 					struct genl_info *info);
+int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb,
+					struct genl_info *info);
 
 extern struct genl_family drm_ras_nl_family;
 
diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
index 50cee70bd065..7a69821b8b78 100644
--- a/include/drm/drm_ras.h
+++ b/include/drm/drm_ras.h
@@ -71,6 +71,19 @@ struct drm_ras_node {
 	 */
 	int (*query_error_threshold)(struct drm_ras_node *node, u32 error_id,
 				     const char **name, u32 *val);
+	/**
+	 * @set_error_threshold:
+	 *
+	 * This callback is used by drm-ras to set threshold value of a specific
+	 * error.
+	 *
+	 * Driver should expect set_error_threshold() to be called with error_id
+	 * from `error_counter_range.first` to `error_counter_range.last`.
+	 *
+	 * Returns: 0 on success, negative error code on failure.
+	 */
+	int (*set_error_threshold)(struct drm_ras_node *node, u32 error_id,
+				   u32 val);
 
 	/** @priv: Driver private data */
 	void *priv;
diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
index 49c5ca497d73..8ff0311d0d63 100644
--- a/include/uapi/drm/drm_ras.h
+++ b/include/uapi/drm/drm_ras.h
@@ -52,6 +52,7 @@ enum {
 	DRM_RAS_CMD_LIST_NODES = 1,
 	DRM_RAS_CMD_GET_ERROR_COUNTER,
 	DRM_RAS_CMD_GET_ERROR_THRESHOLD,
+	DRM_RAS_CMD_SET_ERROR_THRESHOLD,
 
 	__DRM_RAS_CMD_MAX,
 	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)
-- 
2.43.0

[PATCH v1 04/11] drm/xe/uapi: Add additional error components to XE drm_ras

[Raag Jadav]

From: Riana Tauro <riana.tauro@intel.com>

Add additional Error components supported by XE RAS (Reliability,
Availability and Serviceability).

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
Reviewed-by: Aravind Iddamsetty <aravind.iddamsetty@linux.intel.com>
---
 include/uapi/drm/xe_drm.h | 11 ++++++++++-
 1 file changed, 10 insertions(+), 1 deletion(-)

diff --git a/include/uapi/drm/xe_drm.h b/include/uapi/drm/xe_drm.h
index 48e9f1fdb78d..50c80af4ad4e 100644
--- a/include/uapi/drm/xe_drm.h
+++ b/include/uapi/drm/xe_drm.h
@@ -2589,6 +2589,12 @@ enum drm_xe_ras_error_component {
 	DRM_XE_RAS_ERR_COMP_CORE_COMPUTE = 1,
 	/** @DRM_XE_RAS_ERR_COMP_SOC_INTERNAL: SoC Internal Error */
 	DRM_XE_RAS_ERR_COMP_SOC_INTERNAL,
+	/** @DRM_XE_RAS_ERR_COMP_DEVICE_MEMORY: Device Memory Error */
+	DRM_XE_RAS_ERR_COMP_DEVICE_MEMORY,
+	/** @DRM_XE_RAS_ERR_COMP_PCIE: PCIe Subsystem Error */
+	DRM_XE_RAS_ERR_COMP_PCIE,
+	/** @DRM_XE_RAS_ERR_COMP_FABRIC: Fabric Subsystem Error */
+	DRM_XE_RAS_ERR_COMP_FABRIC,
 	/** @DRM_XE_RAS_ERR_COMP_MAX: Max Error */
 	DRM_XE_RAS_ERR_COMP_MAX	/* non-ABI */
 };
@@ -2606,7 +2612,10 @@ enum drm_xe_ras_error_component {
  */
 #define DRM_XE_RAS_ERROR_COMPONENT_NAMES {				\
 	[DRM_XE_RAS_ERR_COMP_CORE_COMPUTE] = "core-compute",		\
-	[DRM_XE_RAS_ERR_COMP_SOC_INTERNAL] = "soc-internal"		\
+	[DRM_XE_RAS_ERR_COMP_SOC_INTERNAL] = "soc-internal",		\
+	[DRM_XE_RAS_ERR_COMP_DEVICE_MEMORY] = "device-memory",		\
+	[DRM_XE_RAS_ERR_COMP_PCIE] = "pcie",				\
+	[DRM_XE_RAS_ERR_COMP_FABRIC] = "fabric",			\
 }
 
 #if defined(__cplusplus)
-- 
2.43.0

[PATCH v1 05/11] drm/xe/sysctrl: Add system controller interrupt handler

[Raag Jadav]

Add system controller interrupt handler which is denoted by 11th bit in
GFX master interrupt register. While at it, add worker for scheduling
system controller work.

Co-developed-by: Soham Purkait <soham.purkait@intel.com>
Signed-off-by: Soham Purkait <soham.purkait@intel.com>
Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
Reviewed-by: Riana Tauro <riana.tauro@intel.com>
---
 drivers/gpu/drm/xe/regs/xe_irq_regs.h |  1 +
 drivers/gpu/drm/xe/xe_irq.c           |  2 ++
 drivers/gpu/drm/xe/xe_sysctrl.c       | 35 +++++++++++++++++++++------
 drivers/gpu/drm/xe/xe_sysctrl.h       |  1 +
 drivers/gpu/drm/xe/xe_sysctrl_types.h |  4 +++
 5 files changed, 36 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/xe/regs/xe_irq_regs.h b/drivers/gpu/drm/xe/regs/xe_irq_regs.h
index 9d74f454d3ff..1d6b976c4de0 100644
--- a/drivers/gpu/drm/xe/regs/xe_irq_regs.h
+++ b/drivers/gpu/drm/xe/regs/xe_irq_regs.h
@@ -22,6 +22,7 @@
 #define   DISPLAY_IRQ				REG_BIT(16)
 #define   SOC_H2DMEMINT_IRQ			REG_BIT(13)
 #define   I2C_IRQ				REG_BIT(12)
+#define   SYSCTRL_IRQ				REG_BIT(11)
 #define   GT_DW_IRQ(x)				REG_BIT(x)
 
 /*
diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
index 9a775c6588dc..e9f0b3cad06d 100644
--- a/drivers/gpu/drm/xe/xe_irq.c
+++ b/drivers/gpu/drm/xe/xe_irq.c
@@ -24,6 +24,7 @@
 #include "xe_mmio.h"
 #include "xe_pxp.h"
 #include "xe_sriov.h"
+#include "xe_sysctrl.h"
 #include "xe_tile.h"
 
 /*
@@ -525,6 +526,7 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg)
 				xe_heci_csc_irq_handler(xe, master_ctl);
 			xe_display_irq_handler(xe, master_ctl);
 			xe_i2c_irq_handler(xe, master_ctl);
+			xe_sysctrl_irq_handler(xe, master_ctl);
 			xe_mert_irq_handler(xe, master_ctl);
 			gu_misc_iir = gu_misc_irq_ack(xe, master_ctl);
 		}
diff --git a/drivers/gpu/drm/xe/xe_sysctrl.c b/drivers/gpu/drm/xe/xe_sysctrl.c
index 2bcef304eb9a..7de3e73bd8e0 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl.c
@@ -8,6 +8,7 @@
 
 #include <drm/drm_managed.h>
 
+#include "regs/xe_irq_regs.h"
 #include "regs/xe_sysctrl_regs.h"
 #include "xe_device.h"
 #include "xe_mmio.h"
@@ -30,10 +31,16 @@
 static void sysctrl_fini(void *arg)
 {
 	struct xe_device *xe = arg;
+	struct xe_sysctrl *sc = &xe->sc;
 
+	disable_work_sync(&sc->work);
 	xe->soc_remapper.set_sysctrl_region(xe, 0);
 }
 
+static void xe_sysctrl_work(struct work_struct *work)
+{
+}
+
 /**
  * xe_sysctrl_init() - Initialize System Controller subsystem
  * @xe: xe device instance
@@ -55,12 +62,6 @@ int xe_sysctrl_init(struct xe_device *xe)
 	if (!xe->info.has_sysctrl)
 		return 0;
 
-	xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX);
-
-	ret = devm_add_action_or_reset(xe->drm.dev, sysctrl_fini, xe);
-	if (ret)
-		return ret;
-
 	sc->mmio = devm_kzalloc(xe->drm.dev, sizeof(*sc->mmio), GFP_KERNEL);
 	if (!sc->mmio)
 		return -ENOMEM;
@@ -73,9 +74,29 @@ int xe_sysctrl_init(struct xe_device *xe)
 	if (ret)
 		return ret;
 
+	xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX);
 	xe_sysctrl_mailbox_init(sc);
+	INIT_WORK(&sc->work, xe_sysctrl_work);
 
-	return 0;
+	return devm_add_action_or_reset(xe->drm.dev, sysctrl_fini, xe);
+}
+
+/**
+ * xe_sysctrl_irq_handler() - Handler for System Controller interrupts
+ * @xe: xe device instance
+ * @master_ctl: interrupt register
+ *
+ * Handle interrupts generated by System Controller.
+ */
+void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl)
+{
+	struct xe_sysctrl *sc = &xe->sc;
+
+	if (!xe->info.has_sysctrl || !sc->work.func)
+		return;
+
+	if (master_ctl & SYSCTRL_IRQ)
+		schedule_work(&sc->work);
 }
 
 /**
diff --git a/drivers/gpu/drm/xe/xe_sysctrl.h b/drivers/gpu/drm/xe/xe_sysctrl.h
index f3b0f3716b2f..f7469bfc9324 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl.h
@@ -17,6 +17,7 @@ static inline struct xe_device *sc_to_xe(struct xe_sysctrl *sc)
 }
 
 int xe_sysctrl_init(struct xe_device *xe);
+void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl);
 void xe_sysctrl_pm_resume(struct xe_device *xe);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_types.h b/drivers/gpu/drm/xe/xe_sysctrl_types.h
index 8217f6befe70..5f408d6491ef 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_types.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_types.h
@@ -8,6 +8,7 @@
 
 #include <linux/mutex.h>
 #include <linux/types.h>
+#include <linux/workqueue_types.h>
 
 struct xe_mmio;
 
@@ -27,6 +28,9 @@ struct xe_sysctrl {
 
 	/** @phase_bit: Message boundary phase toggle bit (0 or 1) */
 	bool phase_bit;
+
+	/** @work: Pending events worker */
+	struct work_struct work;
 };
 
 #endif
-- 
2.43.0

[PATCH v1 06/11] drm/xe/sysctrl: Add system controller event support

[Raag Jadav]

System controller reports different types of events to GFX endpoint for
different usecases, add initial support for them. This will be further
extended to service those usecases.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
---
 drivers/gpu/drm/xe/Makefile                   |  1 +
 drivers/gpu/drm/xe/xe_sysctrl.c               | 11 +++
 drivers/gpu/drm/xe/xe_sysctrl.h               |  1 +
 drivers/gpu/drm/xe/xe_sysctrl_event.c         | 86 +++++++++++++++++++
 drivers/gpu/drm/xe/xe_sysctrl_event_types.h   | 57 ++++++++++++
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h | 18 ++++
 drivers/gpu/drm/xe/xe_sysctrl_types.h         |  3 +
 7 files changed, 177 insertions(+)
 create mode 100644 drivers/gpu/drm/xe/xe_sysctrl_event.c
 create mode 100644 drivers/gpu/drm/xe/xe_sysctrl_event_types.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 3fceda259834..1c863b711ae9 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -126,6 +126,7 @@ xe-y += xe_bb.o \
 	xe_survivability_mode.o \
 	xe_sync.o \
 	xe_sysctrl.o \
+	xe_sysctrl_event.o \
 	xe_sysctrl_mailbox.o \
 	xe_tile.o \
 	xe_tile_sysfs.o \
diff --git a/drivers/gpu/drm/xe/xe_sysctrl.c b/drivers/gpu/drm/xe/xe_sysctrl.c
index 7de3e73bd8e0..6a7da5d2794a 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl.c
@@ -12,6 +12,7 @@
 #include "regs/xe_sysctrl_regs.h"
 #include "xe_device.h"
 #include "xe_mmio.h"
+#include "xe_pm.h"
 #include "xe_soc_remapper.h"
 #include "xe_sysctrl.h"
 #include "xe_sysctrl_mailbox.h"
@@ -39,6 +40,12 @@ static void sysctrl_fini(void *arg)
 
 static void xe_sysctrl_work(struct work_struct *work)
 {
+	struct xe_sysctrl *sc = container_of(work, struct xe_sysctrl, work);
+	struct xe_device *xe = sc_to_xe(sc);
+
+	guard(xe_pm_runtime)(xe);
+	guard(mutex)(&sc->work_lock);
+	xe_sysctrl_event(sc);
 }
 
 /**
@@ -74,6 +81,10 @@ int xe_sysctrl_init(struct xe_device *xe)
 	if (ret)
 		return ret;
 
+	ret = devm_mutex_init(xe->drm.dev, &sc->work_lock);
+	if (ret)
+		return ret;
+
 	xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX);
 	xe_sysctrl_mailbox_init(sc);
 	INIT_WORK(&sc->work, xe_sysctrl_work);
diff --git a/drivers/gpu/drm/xe/xe_sysctrl.h b/drivers/gpu/drm/xe/xe_sysctrl.h
index f7469bfc9324..090dffb6d55f 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl.h
@@ -16,6 +16,7 @@ static inline struct xe_device *sc_to_xe(struct xe_sysctrl *sc)
 	return container_of(sc, struct xe_device, sc);
 }
 
+void xe_sysctrl_event(struct xe_sysctrl *sc);
 int xe_sysctrl_init(struct xe_device *xe);
 void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl);
 void xe_sysctrl_pm_resume(struct xe_device *xe);
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_event.c b/drivers/gpu/drm/xe/xe_sysctrl_event.c
new file mode 100644
index 000000000000..74163e0bafe2
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_sysctrl_event.c
@@ -0,0 +1,86 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#include "xe_device.h"
+#include "xe_irq.h"
+#include "xe_printk.h"
+#include "xe_sysctrl.h"
+#include "xe_sysctrl_event_types.h"
+#include "xe_sysctrl_mailbox.h"
+#include "xe_sysctrl_mailbox_types.h"
+
+static void get_pending_event(struct xe_sysctrl *sc, struct xe_sysctrl_mailbox_command *command)
+{
+	struct xe_sysctrl_event_response *response = command->data_out;
+	struct xe_device *xe = sc_to_xe(sc);
+	u32 count = XE_SYSCTRL_EVENT_FLOOD;
+	size_t len;
+	int ret;
+
+	do {
+		memset(response, 0, sizeof(*response));
+
+		ret = xe_sysctrl_send_command(sc, command, &len);
+		if (ret) {
+			xe_err(xe, "sysctrl: failed to get pending event %d\n", ret);
+			return;
+		}
+
+		if (len != sizeof(*response)) {
+			xe_err(xe, "sysctrl: unexpected event response length %zu (expected %zu)\n",
+			       len, sizeof(*response));
+			return;
+		}
+
+		if (response->event == XE_SYSCTRL_EVENT_THRESHOLD_CROSSED)
+			xe_warn(xe, "[RAS]: counter threshold crossed\n");
+		else
+			xe_err(xe, "sysctrl: unexpected event %#x\n", response->event);
+
+		if (!--count) {
+			xe_err(xe, "sysctrl: event flooding\n");
+			return;
+		}
+
+		xe_dbg(xe, "sysctrl: %u events pending\n", response->count);
+	} while (response->count);
+}
+
+static void event_request_prepare(struct xe_device *xe, struct xe_sysctrl_app_msg_hdr *header,
+				  struct xe_sysctrl_event_request *request)
+{
+	struct pci_dev *pdev = to_pci_dev(xe->drm.dev);
+
+	header->data = REG_FIELD_PREP(APP_HDR_GROUP_ID_MASK, XE_SYSCTRL_GROUP_GFSP) |
+		       REG_FIELD_PREP(APP_HDR_COMMAND_MASK, XE_SYSCTRL_CMD_GET_PENDING_EVENT);
+
+	request->vector = xe_device_has_msix(xe) ? XE_IRQ_DEFAULT_MSIX : 0;
+	request->fn = PCI_FUNC(pdev->devfn);
+}
+
+/**
+ * xe_sysctrl_event() - Handler for System Controller events
+ * @sc: System Controller instance
+ *
+ * Handle events generated by System Controller.
+ */
+void xe_sysctrl_event(struct xe_sysctrl *sc)
+{
+	struct xe_sysctrl_mailbox_command command = {};
+	struct xe_sysctrl_event_response response = {};
+	struct xe_sysctrl_event_request request = {};
+	struct xe_sysctrl_app_msg_hdr header = {};
+
+	xe_device_assert_mem_access(sc_to_xe(sc));
+	event_request_prepare(sc_to_xe(sc), &header, &request);
+
+	command.header = header;
+	command.data_in = &request;
+	command.data_in_len = sizeof(request);
+	command.data_out = &response;
+	command.data_out_len = sizeof(response);
+
+	get_pending_event(sc, &command);
+}
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_event_types.h b/drivers/gpu/drm/xe/xe_sysctrl_event_types.h
new file mode 100644
index 000000000000..4d444ba40b9b
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_sysctrl_event_types.h
@@ -0,0 +1,57 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef _XE_SYSCTRL_EVENT_TYPES_H_
+#define _XE_SYSCTRL_EVENT_TYPES_H_
+
+#include <linux/types.h>
+
+#define XE_SYSCTRL_EVENT_DATA_LEN		59
+
+/* Modify as needed */
+#define XE_SYSCTRL_EVENT_FLOOD			16
+
+/**
+ * enum xe_sysctrl_event - Events reported by System Controller
+ *
+ * @XE_SYSCTRL_EVENT_THRESHOLD_CROSSED: Error counter threshold crossed
+ */
+enum xe_sysctrl_event {
+	XE_SYSCTRL_EVENT_THRESHOLD_CROSSED	= 0x01,
+};
+
+/**
+ * struct xe_sysctrl_event_request - Request structure for pending event
+ */
+struct xe_sysctrl_event_request {
+	/** @vector: MSI-X vector that was triggered */
+	u32 vector;
+	/** @fn: Function index (0-7) of PCIe device */
+	u32 fn:8;
+	/** @reserved: Reserved for future use */
+	u32 reserved:24;
+	/** @reserved2: Reserved for future use */
+	u32 reserved2[2];
+} __packed;
+
+/**
+ * struct xe_sysctrl_event_response - Response structure for pending event
+ */
+struct xe_sysctrl_event_response {
+	/** @count: Pending event count, decremented by fw on each response */
+	u32 count;
+	/** @event: Pending event type */
+	u32 event;
+	/** @timestamp: Timestamp of most recent event */
+	u64 timestamp;
+	/** @extended: Event has extended payload */
+	u32 extended:1;
+	/** @reserved: Reserved for future use */
+	u32 reserved:31;
+	/** @data: Generic event data */
+	u32 data[XE_SYSCTRL_EVENT_DATA_LEN];
+} __packed;
+
+#endif /* _XE_SYSCTRL_EVENT_TYPES_H_ */
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
index 89456aec6097..84d7c647e743 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
@@ -10,6 +10,24 @@
 
 #include "abi/xe_sysctrl_abi.h"
 
+/**
+ * enum xe_sysctrl_group - System Controller command groups
+ *
+ * @XE_SYSCTRL_GROUP_GFSP: GFSP group
+ */
+enum xe_sysctrl_group {
+	XE_SYSCTRL_GROUP_GFSP			= 0x01,
+};
+
+/**
+ * enum xe_sysctrl_gfsp_cmd - Commands supported by GFSP group
+ *
+ * @XE_SYSCTRL_CMD_GET_PENDING_EVENT: Retrieve pending event
+ */
+enum xe_sysctrl_gfsp_cmd {
+	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
+};
+
 /**
  * struct xe_sysctrl_mailbox_command - System Controller mailbox command
  */
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_types.h b/drivers/gpu/drm/xe/xe_sysctrl_types.h
index 5f408d6491ef..95359af691c9 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_types.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_types.h
@@ -31,6 +31,9 @@ struct xe_sysctrl {
 
 	/** @work: Pending events worker */
 	struct work_struct work;
+
+	/** @work_lock: Mutex protecting pending events */
+	struct mutex work_lock;
 };
 
 #endif
-- 
2.43.0

[PATCH v1 07/11] drm/xe/ras: Introduce correctable error handling

[Raag Jadav]

Add initial support for correctable error handling which is serviced
using system controller event. Currently we only log the errors in
dmesg but this serves as a foundation for RAS infrastructure and will
be further extended to facilitate other RAS features.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
---
 drivers/gpu/drm/xe/Makefile           |  1 +
 drivers/gpu/drm/xe/xe_ras.c           | 92 +++++++++++++++++++++++++++
 drivers/gpu/drm/xe/xe_ras.h           | 15 +++++
 drivers/gpu/drm/xe/xe_ras_types.h     | 73 +++++++++++++++++++++
 drivers/gpu/drm/xe/xe_sysctrl_event.c |  3 +-
 5 files changed, 183 insertions(+), 1 deletion(-)
 create mode 100644 drivers/gpu/drm/xe/xe_ras.c
 create mode 100644 drivers/gpu/drm/xe/xe_ras.h
 create mode 100644 drivers/gpu/drm/xe/xe_ras_types.h

diff --git a/drivers/gpu/drm/xe/Makefile b/drivers/gpu/drm/xe/Makefile
index 1c863b711ae9..22f17bd1082d 100644
--- a/drivers/gpu/drm/xe/Makefile
+++ b/drivers/gpu/drm/xe/Makefile
@@ -114,6 +114,7 @@ xe-y += xe_bb.o \
 	xe_pxp_submit.o \
 	xe_query.o \
 	xe_range_fence.o \
+	xe_ras.o \
 	xe_reg_sr.o \
 	xe_reg_whitelist.o \
 	xe_ring_ops.o \
diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
new file mode 100644
index 000000000000..08e91348c459
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -0,0 +1,92 @@
+// SPDX-License-Identifier: MIT
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#include "xe_printk.h"
+#include "xe_ras.h"
+#include "xe_ras_types.h"
+#include "xe_sysctrl.h"
+#include "xe_sysctrl_event_types.h"
+
+/* Severity of detected errors  */
+enum xe_ras_severity {
+	XE_RAS_SEV_NOT_SUPPORTED = 0,
+	XE_RAS_SEV_CORRECTABLE,
+	XE_RAS_SEV_UNCORRECTABLE,
+	XE_RAS_SEV_INFORMATIONAL,
+	XE_RAS_SEV_MAX
+};
+
+/* Major IP blocks/components where errors can originate */
+enum xe_ras_component {
+	XE_RAS_COMP_NOT_SUPPORTED = 0,
+	XE_RAS_COMP_DEVICE_MEMORY,
+	XE_RAS_COMP_CORE_COMPUTE,
+	XE_RAS_COMP_RESERVED,
+	XE_RAS_COMP_PCIE,
+	XE_RAS_COMP_FABRIC,
+	XE_RAS_COMP_SOC_INTERNAL,
+	XE_RAS_COMP_MAX
+};
+
+static const char *const xe_ras_severities[] = {
+	[XE_RAS_SEV_NOT_SUPPORTED]		= "Not Supported",
+	[XE_RAS_SEV_CORRECTABLE]		= "Correctable Error",
+	[XE_RAS_SEV_UNCORRECTABLE]		= "Uncorrectable Error",
+	[XE_RAS_SEV_INFORMATIONAL]		= "Informational Error",
+};
+static_assert(ARRAY_SIZE(xe_ras_severities) == XE_RAS_SEV_MAX);
+
+static const char *const xe_ras_components[] = {
+	[XE_RAS_COMP_NOT_SUPPORTED]		= "Not Supported",
+	[XE_RAS_COMP_DEVICE_MEMORY]		= "Device Memory",
+	[XE_RAS_COMP_CORE_COMPUTE]		= "Core Compute",
+	[XE_RAS_COMP_RESERVED]			= "Reserved",
+	[XE_RAS_COMP_PCIE]			= "PCIe",
+	[XE_RAS_COMP_FABRIC]			= "Fabric",
+	[XE_RAS_COMP_SOC_INTERNAL]		= "SoC Internal",
+};
+static_assert(ARRAY_SIZE(xe_ras_components) == XE_RAS_COMP_MAX);
+
+static inline const char *sev_to_str(u8 sev)
+{
+	if (sev >= XE_RAS_SEV_MAX)
+		sev = XE_RAS_SEV_NOT_SUPPORTED;
+
+	return xe_ras_severities[sev];
+}
+
+static inline const char *comp_to_str(u8 comp)
+{
+	if (comp >= XE_RAS_COMP_MAX)
+		comp = XE_RAS_COMP_NOT_SUPPORTED;
+
+	return xe_ras_components[comp];
+}
+
+void xe_ras_counter_threshold_crossed(struct xe_device *xe,
+				      struct xe_sysctrl_event_response *response)
+{
+	struct xe_ras_threshold_crossed *pending = (void *)&response->data;
+	struct xe_ras_error_class *errors = pending->counters;
+	u32 counter_id, ncounters = pending->ncounters;
+
+	if (!ncounters || ncounters > XE_RAS_NUM_COUNTERS) {
+		xe_err(xe, "sysctrl: unexpected counter threshold crossed %u\n", ncounters);
+		return;
+	}
+
+	BUILD_BUG_ON(sizeof(response->data) < sizeof(*pending));
+	xe_warn(xe, "[RAS]: counter threshold crossed, %u new errors\n", ncounters);
+
+	for (counter_id = 0; counter_id < ncounters; counter_id++) {
+		u8 severity, component;
+
+		severity = errors[counter_id].common.severity;
+		component = errors[counter_id].common.component;
+
+		xe_warn(xe, "[RAS]: %s %s detected\n",
+			comp_to_str(component), sev_to_str(severity));
+	}
+}
diff --git a/drivers/gpu/drm/xe/xe_ras.h b/drivers/gpu/drm/xe/xe_ras.h
new file mode 100644
index 000000000000..ea90593b62dc
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_ras.h
@@ -0,0 +1,15 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef _XE_RAS_H_
+#define _XE_RAS_H_
+
+struct xe_device;
+struct xe_sysctrl_event_response;
+
+void xe_ras_counter_threshold_crossed(struct xe_device *xe,
+				      struct xe_sysctrl_event_response *response);
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
new file mode 100644
index 000000000000..4e63c67f806a
--- /dev/null
+++ b/drivers/gpu/drm/xe/xe_ras_types.h
@@ -0,0 +1,73 @@
+/* SPDX-License-Identifier: MIT */
+/*
+ * Copyright © 2026 Intel Corporation
+ */
+
+#ifndef _XE_RAS_TYPES_H_
+#define _XE_RAS_TYPES_H_
+
+#include <linux/types.h>
+
+#define XE_RAS_NUM_COUNTERS			16
+
+/**
+ * struct xe_ras_error_common - Error fields that are common across all products
+ */
+struct xe_ras_error_common {
+	/** @severity: Error severity */
+	u8 severity;
+	/** @component: IP block where error originated */
+	u8 component;
+} __packed;
+
+/**
+ * struct xe_ras_error_unit - Error unit information
+ */
+struct xe_ras_error_unit {
+	/** @tile: Tile identifier */
+	u8 tile;
+	/** @instance: Instance identifier specific to IP */
+	u32 instance;
+} __packed;
+
+/**
+ * struct xe_ras_error_cause - Error cause information
+ */
+struct xe_ras_error_cause {
+	/** @cause: Cause/checker */
+	u32 cause;
+	/** @reserved: For future use */
+	u8 reserved;
+} __packed;
+
+/**
+ * struct xe_ras_error_product - Error fields that are specific to the product
+ */
+struct xe_ras_error_product {
+	/** @unit: Unit within IP block */
+	struct xe_ras_error_unit unit;
+	/** @cause: Cause/checker */
+	struct xe_ras_error_cause cause;
+} __packed;
+
+/**
+ * struct xe_ras_error_class - Combines common and product-specific parts
+ */
+struct xe_ras_error_class {
+	/** @common: Common error type and component */
+	struct xe_ras_error_common common;
+	/** @product: Product-specific unit and cause */
+	struct xe_ras_error_product product;
+} __packed;
+
+/**
+ * struct xe_ras_threshold_crossed - Data for threshold crossed event
+ */
+struct xe_ras_threshold_crossed {
+	/** @ncounters: Number of error counters that crossed thresholds */
+	u32 ncounters;
+	/** @counters: Array of error counters that crossed threshold */
+	struct xe_ras_error_class counters[XE_RAS_NUM_COUNTERS];
+} __packed;
+
+#endif
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_event.c b/drivers/gpu/drm/xe/xe_sysctrl_event.c
index 74163e0bafe2..e96af8be07a2 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_event.c
+++ b/drivers/gpu/drm/xe/xe_sysctrl_event.c
@@ -6,6 +6,7 @@
 #include "xe_device.h"
 #include "xe_irq.h"
 #include "xe_printk.h"
+#include "xe_ras.h"
 #include "xe_sysctrl.h"
 #include "xe_sysctrl_event_types.h"
 #include "xe_sysctrl_mailbox.h"
@@ -35,7 +36,7 @@ static void get_pending_event(struct xe_sysctrl *sc, struct xe_sysctrl_mailbox_c
 		}
 
 		if (response->event == XE_SYSCTRL_EVENT_THRESHOLD_CROSSED)
-			xe_warn(xe, "[RAS]: counter threshold crossed\n");
+			xe_ras_counter_threshold_crossed(xe, response);
 		else
 			xe_err(xe, "sysctrl: unexpected event %#x\n", response->event);
 
-- 
2.43.0

[PATCH v1 08/11] drm/xe/ras: Get error threshold support

[Raag Jadav]

System controller allows programming per error threshold value, which
it uses to raise error events to the driver. Get it using mailbox
command so that it can be exposed to the user.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 drivers/gpu/drm/xe/xe_ras.c                   | 73 +++++++++++++++++++
 drivers/gpu/drm/xe/xe_ras.h                   |  3 +
 drivers/gpu/drm/xe/xe_ras_types.h             | 22 ++++++
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |  2 +
 4 files changed, 100 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 08e91348c459..3e93f838aa4a 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -3,11 +3,14 @@
  * Copyright © 2026 Intel Corporation
  */
 
+#include "xe_pm.h"
 #include "xe_printk.h"
 #include "xe_ras.h"
 #include "xe_ras_types.h"
 #include "xe_sysctrl.h"
 #include "xe_sysctrl_event_types.h"
+#include "xe_sysctrl_mailbox.h"
+#include "xe_sysctrl_mailbox_types.h"
 
 /* Severity of detected errors  */
 enum xe_ras_severity {
@@ -49,6 +52,23 @@ static const char *const xe_ras_components[] = {
 };
 static_assert(ARRAY_SIZE(xe_ras_components) == XE_RAS_COMP_MAX);
 
+/* uAPI mapping */
+static const int drm_to_xe_ras_components[] = {
+	[DRM_XE_RAS_ERR_COMP_CORE_COMPUTE]	= XE_RAS_COMP_CORE_COMPUTE,
+	[DRM_XE_RAS_ERR_COMP_SOC_INTERNAL]	= XE_RAS_COMP_SOC_INTERNAL,
+	[DRM_XE_RAS_ERR_COMP_DEVICE_MEMORY]	= XE_RAS_COMP_DEVICE_MEMORY,
+	[DRM_XE_RAS_ERR_COMP_PCIE]		= XE_RAS_COMP_PCIE,
+	[DRM_XE_RAS_ERR_COMP_FABRIC]		= XE_RAS_COMP_FABRIC
+};
+static_assert(ARRAY_SIZE(drm_to_xe_ras_components) == DRM_XE_RAS_ERR_COMP_MAX);
+
+/* uAPI mapping */
+static const int drm_to_xe_ras_severities[] = {
+	[DRM_XE_RAS_ERR_SEV_CORRECTABLE]	= XE_RAS_SEV_CORRECTABLE,
+	[DRM_XE_RAS_ERR_SEV_UNCORRECTABLE]	= XE_RAS_SEV_UNCORRECTABLE
+};
+static_assert(ARRAY_SIZE(drm_to_xe_ras_severities) == DRM_XE_RAS_ERR_SEV_MAX);
+
 static inline const char *sev_to_str(u8 sev)
 {
 	if (sev >= XE_RAS_SEV_MAX)
@@ -90,3 +110,56 @@ void xe_ras_counter_threshold_crossed(struct xe_device *xe,
 			comp_to_str(component), sev_to_str(severity));
 	}
 }
+
+static void ras_command_prepare(struct xe_sysctrl_mailbox_command *command,
+				void *request, size_t request_len, void *response,
+				size_t response_len, u8 hdr_cmd)
+{
+	struct xe_sysctrl_app_msg_hdr header = {};
+
+	header.data = REG_FIELD_PREP(APP_HDR_GROUP_ID_MASK, XE_SYSCTRL_GROUP_GFSP) |
+		      REG_FIELD_PREP(APP_HDR_COMMAND_MASK, hdr_cmd);
+
+	command->header = header;
+	command->data_in = request;
+	command->data_in_len = request_len;
+	command->data_out = response;
+	command->data_out_len = response_len;
+}
+
+int xe_ras_get_threshold(struct xe_device *xe, u32 severity, u32 component, u32 *threshold)
+{
+	struct xe_ras_get_threshold_response response = {};
+	struct xe_ras_get_threshold_request request = {};
+	struct xe_sysctrl_mailbox_command command = {};
+	struct xe_ras_error_class counter = {};
+	size_t len;
+	int ret;
+
+	counter.common.severity = drm_to_xe_ras_severities[severity];
+	counter.common.component = drm_to_xe_ras_components[component];
+	request.counter = counter;
+
+	ras_command_prepare(&command, &request, sizeof(request), &response,
+			    sizeof(response), XE_SYSCTRL_CMD_GET_THRESHOLD);
+
+	guard(xe_pm_runtime)(xe);
+	ret = xe_sysctrl_send_command(&xe->sc, &command, &len);
+	if (ret) {
+		xe_err(xe, "sysctrl: failed to get threshold %d\n", ret);
+		return ret;
+	}
+
+	if (len != sizeof(response)) {
+		xe_err(xe, "sysctrl: unexpected get threshold response length %zu (expected %zu)\n",
+		       len, sizeof(response));
+		return -EIO;
+	}
+
+	counter = response.counter;
+	*threshold = response.threshold;
+
+	xe_dbg(xe, "[RAS]: Get threshold %u for %s %s\n", response.threshold,
+	       comp_to_str(counter.common.component), sev_to_str(counter.common.severity));
+	return 0;
+}
diff --git a/drivers/gpu/drm/xe/xe_ras.h b/drivers/gpu/drm/xe/xe_ras.h
index ea90593b62dc..982bbe61461e 100644
--- a/drivers/gpu/drm/xe/xe_ras.h
+++ b/drivers/gpu/drm/xe/xe_ras.h
@@ -6,10 +6,13 @@
 #ifndef _XE_RAS_H_
 #define _XE_RAS_H_
 
+#include <linux/types.h>
+
 struct xe_device;
 struct xe_sysctrl_event_response;
 
 void xe_ras_counter_threshold_crossed(struct xe_device *xe,
 				      struct xe_sysctrl_event_response *response);
+int xe_ras_get_threshold(struct xe_device *xe, u32 severity, u32 component, u32 *threshold);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
index 4e63c67f806a..d5da93d65cf5 100644
--- a/drivers/gpu/drm/xe/xe_ras_types.h
+++ b/drivers/gpu/drm/xe/xe_ras_types.h
@@ -70,4 +70,26 @@ struct xe_ras_threshold_crossed {
 	struct xe_ras_error_class counters[XE_RAS_NUM_COUNTERS];
 } __packed;
 
+/**
+ * struct xe_ras_get_threshold_request - Request structure for get threshold
+ */
+struct xe_ras_get_threshold_request {
+	/** @counter: Counter to get threshold for */
+	struct xe_ras_error_class counter;
+	/** @reserved: Reserved for future use */
+	u32 reserved;
+} __packed;
+
+/**
+ * struct xe_ras_get_threshold_response - Response structure for get threshold
+ */
+struct xe_ras_get_threshold_response {
+	/** @counter: Counter id */
+	struct xe_ras_error_class counter;
+	/** @threshold: Threshold value */
+	u32 threshold;
+	/** @reserved: Reserved for future use */
+	u32 reserved[4];
+} __packed;
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
index 84d7c647e743..a1b71218deca 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
@@ -22,9 +22,11 @@ enum xe_sysctrl_group {
 /**
  * enum xe_sysctrl_gfsp_cmd - Commands supported by GFSP group
  *
+ * @XE_SYSCTRL_CMD_GET_THRESHOLD: Retrieve error threshold
  * @XE_SYSCTRL_CMD_GET_PENDING_EVENT: Retrieve pending event
  */
 enum xe_sysctrl_gfsp_cmd {
+	XE_SYSCTRL_CMD_GET_THRESHOLD		= 0x05,
 	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
 };
 
-- 
2.43.0

[PATCH v1 09/11] drm/xe/ras: Set error threshold support

[Raag Jadav]

System controller allows programming per error threshold value, which
it uses to raise error events to the driver. Set it using mailbox
command so that it can be programmed by the user.

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 drivers/gpu/drm/xe/xe_ras.c                   | 42 +++++++++++++++++++
 drivers/gpu/drm/xe/xe_ras.h                   |  1 +
 drivers/gpu/drm/xe/xe_ras_types.h             | 28 +++++++++++++
 drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h |  2 +
 4 files changed, 73 insertions(+)

diff --git a/drivers/gpu/drm/xe/xe_ras.c b/drivers/gpu/drm/xe/xe_ras.c
index 3e93f838aa4a..26e063166c5f 100644
--- a/drivers/gpu/drm/xe/xe_ras.c
+++ b/drivers/gpu/drm/xe/xe_ras.c
@@ -163,3 +163,45 @@ int xe_ras_get_threshold(struct xe_device *xe, u32 severity, u32 component, u32
 	       comp_to_str(counter.common.component), sev_to_str(counter.common.severity));
 	return 0;
 }
+
+int xe_ras_set_threshold(struct xe_device *xe, u32 severity, u32 component, u32 threshold)
+{
+	struct xe_ras_set_threshold_response response = {};
+	struct xe_ras_set_threshold_request request = {};
+	struct xe_sysctrl_mailbox_command command = {};
+	struct xe_ras_error_class counter = {};
+	size_t len;
+	int ret;
+
+	counter.common.severity = drm_to_xe_ras_severities[severity];
+	counter.common.component = drm_to_xe_ras_components[component];
+	request.counter = counter;
+	request.threshold = threshold;
+
+	ras_command_prepare(&command, &request, sizeof(request), &response,
+			    sizeof(response), XE_SYSCTRL_CMD_SET_THRESHOLD);
+
+	guard(xe_pm_runtime)(xe);
+	ret = xe_sysctrl_send_command(&xe->sc, &command, &len);
+	if (ret) {
+		xe_err(xe, "sysctrl: failed to set threshold %d\n", ret);
+		return ret;
+	}
+
+	if (len != sizeof(response)) {
+		xe_err(xe, "sysctrl: unexpected set threshold response length %zu (expected %zu)\n",
+		       len, sizeof(response));
+		return -EIO;
+	}
+
+	if (response.status) {
+		xe_err(xe, "sysctrl: set threshold operation failed %#x\n", response.status);
+		return -EIO;
+	}
+
+	counter = response.counter;
+
+	xe_dbg(xe, "[RAS]: Set threshold %u for %s %s\n", response.threshold,
+	       comp_to_str(counter.common.component), sev_to_str(counter.common.severity));
+	return 0;
+}
diff --git a/drivers/gpu/drm/xe/xe_ras.h b/drivers/gpu/drm/xe/xe_ras.h
index 982bbe61461e..d1f71b1de723 100644
--- a/drivers/gpu/drm/xe/xe_ras.h
+++ b/drivers/gpu/drm/xe/xe_ras.h
@@ -14,5 +14,6 @@ struct xe_sysctrl_event_response;
 void xe_ras_counter_threshold_crossed(struct xe_device *xe,
 				      struct xe_sysctrl_event_response *response);
 int xe_ras_get_threshold(struct xe_device *xe, u32 severity, u32 component, u32 *threshold);
+int xe_ras_set_threshold(struct xe_device *xe, u32 severity, u32 component, u32 threshold);
 
 #endif
diff --git a/drivers/gpu/drm/xe/xe_ras_types.h b/drivers/gpu/drm/xe/xe_ras_types.h
index d5da93d65cf5..d7e4a02a661d 100644
--- a/drivers/gpu/drm/xe/xe_ras_types.h
+++ b/drivers/gpu/drm/xe/xe_ras_types.h
@@ -92,4 +92,32 @@ struct xe_ras_get_threshold_response {
 	u32 reserved[4];
 } __packed;
 
+/**
+ * struct xe_ras_set_threshold_request - Request structure for set threshold
+ */
+struct xe_ras_set_threshold_request {
+	/** @counter: Counter to set threshold for */
+	struct xe_ras_error_class counter;
+	/** @threshold: Threshold value to set */
+	u32 threshold;
+	/** @reserved: Reserved for future use */
+	u32 reserved;
+} __packed;
+
+/**
+ * struct xe_ras_set_threshold_response - Response structure for set threshold
+ */
+struct xe_ras_set_threshold_response {
+	/** @counter: Counter id */
+	struct xe_ras_error_class counter;
+	/** @threshold_old: Old threshold value */
+	u32 threshold_old;
+	/** @threshold: New threshold value */
+	u32 threshold;
+	/** @status: Set threshold operation status */
+	u32 status;
+	/** @reserved: Reserved for future use */
+	u32 reserved[2];
+} __packed;
+
 #endif
diff --git a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
index a1b71218deca..b865768e903b 100644
--- a/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
+++ b/drivers/gpu/drm/xe/xe_sysctrl_mailbox_types.h
@@ -23,10 +23,12 @@ enum xe_sysctrl_group {
  * enum xe_sysctrl_gfsp_cmd - Commands supported by GFSP group
  *
  * @XE_SYSCTRL_CMD_GET_THRESHOLD: Retrieve error threshold
+ * @XE_SYSCTRL_CMD_SET_THRESHOLD: Set error threshold
  * @XE_SYSCTRL_CMD_GET_PENDING_EVENT: Retrieve pending event
  */
 enum xe_sysctrl_gfsp_cmd {
 	XE_SYSCTRL_CMD_GET_THRESHOLD		= 0x05,
+	XE_SYSCTRL_CMD_SET_THRESHOLD		= 0x06,
 	XE_SYSCTRL_CMD_GET_PENDING_EVENT	= 0x07,
 };
 
-- 
2.43.0

[PATCH v1 10/11] drm/xe/drm_ras: Wire up error threshold callbacks

[Raag Jadav]

Now that we have get/set error threshold support in xe driver, wire them
up to drm_ras so that the user can make use of both functionalities.

$ sudo ynl --family drm_ras --do get-error-threshold --json \
  '{"node-id":0, "error-id":2}'
{'error-id': 2, 'error-name': 'soc-internal', 'error-threshold': 0}

$ sudo ynl --family drm_ras --do set-error-threshold --json \
  '{"node-id":0, "error-id":2, "error-threshold":8}'
None

Signed-off-by: Raag Jadav <raag.jadav@intel.com>
---
 drivers/gpu/drm/xe/xe_drm_ras.c | 29 +++++++++++++++++++++++++++--
 1 file changed, 27 insertions(+), 2 deletions(-)

diff --git a/drivers/gpu/drm/xe/xe_drm_ras.c b/drivers/gpu/drm/xe/xe_drm_ras.c
index e07dc23a155e..824dabd5c29e 100644
--- a/drivers/gpu/drm/xe/xe_drm_ras.c
+++ b/drivers/gpu/drm/xe/xe_drm_ras.c
@@ -11,6 +11,7 @@
 
 #include "xe_device_types.h"
 #include "xe_drm_ras.h"
+#include "xe_ras.h"
 
 static const char * const error_components[] = DRM_XE_RAS_ERROR_COMPONENT_NAMES;
 static const char * const error_severity[] = DRM_XE_RAS_ERROR_SEVERITY_NAMES;
@@ -47,6 +48,27 @@ static int query_correctable_error_counter(struct drm_ras_node *ep, u32 error_id
 	return hw_query_error_counter(info, error_id, name, val);
 }
 
+static int query_correctable_error_threshold(struct drm_ras_node *ep, u32 error_id,
+					     const char **name, u32 *val)
+{
+	struct xe_device *xe = ep->priv;
+
+	if (!xe->info.has_sysctrl)
+		return -EOPNOTSUPP;
+
+	return xe_ras_get_threshold(xe, DRM_XE_RAS_ERR_SEV_CORRECTABLE, error_id, val);
+}
+
+static int set_correctable_error_threshold(struct drm_ras_node *ep, u32 error_id, u32 val)
+{
+	struct xe_device *xe = ep->priv;
+
+	if (!xe->info.has_sysctrl)
+		return -EOPNOTSUPP;
+
+	return xe_ras_set_threshold(xe, DRM_XE_RAS_ERR_SEV_CORRECTABLE, error_id, val);
+}
+
 static struct xe_drm_ras_counter *allocate_and_copy_counters(struct xe_device *xe)
 {
 	struct xe_drm_ras_counter *counter;
@@ -92,10 +114,13 @@ static int assign_node_params(struct xe_device *xe, struct drm_ras_node *node,
 	if (IS_ERR(ras->info[severity]))
 		return PTR_ERR(ras->info[severity]);
 
-	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE)
+	if (severity == DRM_XE_RAS_ERR_SEV_CORRECTABLE) {
 		node->query_error_counter = query_correctable_error_counter;
-	else
+		node->query_error_threshold = query_correctable_error_threshold;
+		node->set_error_threshold = set_correctable_error_threshold;
+	} else {
 		node->query_error_counter = query_uncorrectable_error_counter;
+	}
 
 	return 0;
 }
-- 
2.43.0

[PATCH v1 11/11] drm/xe/ras: Add flag for Xe RAS

[Raag Jadav]

From: Riana Tauro <riana.tauro@intel.com>

Add a flag for RAS. If enabled, XE driver registers with
drm_ras and exposes supported counters.

Currently this is enabled for PVC and CRI.

Signed-off-by: Riana Tauro <riana.tauro@intel.com>
---
 drivers/gpu/drm/xe/xe_device_types.h | 2 ++
 drivers/gpu/drm/xe/xe_hw_error.c     | 2 +-
 drivers/gpu/drm/xe/xe_pci.c          | 3 +++
 drivers/gpu/drm/xe/xe_pci_types.h    | 1 +
 4 files changed, 7 insertions(+), 1 deletion(-)

diff --git a/drivers/gpu/drm/xe/xe_device_types.h b/drivers/gpu/drm/xe/xe_device_types.h
index 31df9debcbb0..7a8afd06e6b8 100644
--- a/drivers/gpu/drm/xe/xe_device_types.h
+++ b/drivers/gpu/drm/xe/xe_device_types.h
@@ -191,6 +191,8 @@ struct xe_device {
 		u8 has_ctx_tlb_inval:1;
 		/** @info.has_range_tlb_inval: Has range based TLB invalidations */
 		u8 has_range_tlb_inval:1;
+		/** @info.has_ras: Device supports RAS (Reliability, Availability, Serviceability) */
+		u8 has_ras:1;
 		/** @info.has_soc_remapper_sysctrl: Has SoC remapper system controller */
 		u8 has_soc_remapper_sysctrl:1;
 		/** @info.has_soc_remapper_telem: Has SoC remapper telemetry support */
diff --git a/drivers/gpu/drm/xe/xe_hw_error.c b/drivers/gpu/drm/xe/xe_hw_error.c
index 2a31b430570e..3ab0fceb151f 100644
--- a/drivers/gpu/drm/xe/xe_hw_error.c
+++ b/drivers/gpu/drm/xe/xe_hw_error.c
@@ -520,7 +520,7 @@ void xe_hw_error_irq_handler(struct xe_tile *tile, const u32 master_ctl)
 
 static int hw_error_info_init(struct xe_device *xe)
 {
-	if (xe->info.platform != XE_PVC)
+	if (!xe->info.has_ras)
 		return 0;
 
 	return xe_drm_ras_init(xe);
diff --git a/drivers/gpu/drm/xe/xe_pci.c b/drivers/gpu/drm/xe/xe_pci.c
index 278c2860a4f6..10ff207affa9 100644
--- a/drivers/gpu/drm/xe/xe_pci.c
+++ b/drivers/gpu/drm/xe/xe_pci.c
@@ -365,6 +365,7 @@ static const __maybe_unused struct xe_device_desc pvc_desc = {
 	.vm_max_level = 4,
 	.vram_flags = XE_VRAM_FLAGS_NEED64K,
 	.has_mbx_power_limits = false,
+	.has_ras = true,
 };
 
 static const struct xe_device_desc mtl_desc = {
@@ -472,6 +473,7 @@ static const struct xe_device_desc cri_desc = {
 	.require_force_probe = true,
 	.va_bits = 57,
 	.vm_max_level = 4,
+	.has_ras = true,
 };
 
 static const struct xe_device_desc nvlp_desc = {
@@ -761,6 +763,7 @@ static int xe_info_init_early(struct xe_device *xe,
 	xe->info.has_page_reclaim_hw_assist = desc->has_page_reclaim_hw_assist;
 	xe->info.has_pre_prod_wa = desc->has_pre_prod_wa;
 	xe->info.has_pxp = desc->has_pxp;
+	xe->info.has_ras = desc->has_ras;
 	xe->info.has_soc_remapper_sysctrl = desc->has_soc_remapper_sysctrl;
 	xe->info.has_soc_remapper_telem = desc->has_soc_remapper_telem;
 	xe->info.has_sriov = xe_configfs_primary_gt_allowed(to_pci_dev(xe->drm.dev)) &&
diff --git a/drivers/gpu/drm/xe/xe_pci_types.h b/drivers/gpu/drm/xe/xe_pci_types.h
index 5b85e2c24b7b..70a9d4995cbd 100644
--- a/drivers/gpu/drm/xe/xe_pci_types.h
+++ b/drivers/gpu/drm/xe/xe_pci_types.h
@@ -54,6 +54,7 @@ struct xe_device_desc {
 	u8 has_pre_prod_wa:1;
 	u8 has_page_reclaim_hw_assist:1;
 	u8 has_pxp:1;
+	u8 has_ras:1;
 	u8 has_soc_remapper_sysctrl:1;
 	u8 has_soc_remapper_telem:1;
 	u8 has_sriov:1;
-- 
2.43.0

Re: [PATCH v1 02/11] drm/ras: Introduce get-error-threshold

[Tauro, Riana]

On 4/18/2026 2:46 AM, Raag Jadav wrote:
> Add get-error-threshold command support which allows querying threshold
> value of the error. Threshold in RAS context means the number of errors
> the hardware is expected to accumulate before it raises them to software.
> This is to have a fine grained control over error notifications that are
> raised by the hardware.
>
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> ---
>   Documentation/gpu/drm-ras.rst            |   8 ++
>   Documentation/netlink/specs/drm_ras.yaml |  37 ++++++++
>   drivers/gpu/drm/drm_ras.c                | 103 +++++++++++++++++++++++
>   drivers/gpu/drm/drm_ras_nl.c             |  13 +++
>   drivers/gpu/drm/drm_ras_nl.h             |   2 +
>   include/drm/drm_ras.h                    |  14 +++
>   include/uapi/drm/drm_ras.h               |  11 +++
>   7 files changed, 188 insertions(+)
>
> diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
> index 70b246a78fc8..6443dfd1677f 100644
> --- a/Documentation/gpu/drm-ras.rst
> +++ b/Documentation/gpu/drm-ras.rst
> @@ -52,6 +52,8 @@ User space tools can:
>     as a parameter.
>   * Query specific error counter values with the ``get-error-counter`` command, using both
>     ``node-id`` and ``error-id`` as parameters.
> +* Query specific error threshold value with the ``get-error-threshold`` command, using both
> +  ``node-id`` and ``error-id`` as parameters.
Also define what is a thresold. How can it be used?
>   
>   YAML-based Interface
>   --------------------
> @@ -101,3 +103,9 @@ Example: Query an error counter for a given node
>       sudo ynl --family drm_ras --do get-error-counter --json '{"node-id":0, "error-id":1}'
>       {'error-id': 1, 'error-name': 'error_name1', 'error-value': 0}
>   
> +Example: Query threshold value of a given error
> +
> +.. code-block:: bash
> +
> +    sudo ynl --family drm_ras --do get-error-threshold --json '{"node-id":0, "error-id":1}'
> +    {'error-id': 1, 'error-name': 'error_name1', 'error-threshold': 0}
> diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
> index 79af25dac3c5..95a939fb987d 100644
> --- a/Documentation/netlink/specs/drm_ras.yaml
> +++ b/Documentation/netlink/specs/drm_ras.yaml
> @@ -69,6 +69,25 @@ attribute-sets:
>           name: error-value
>           type: u32
>           doc: Current value of the requested error counter.
> +  -
> +    name: error-threshold-attrs
> +    attributes:
> +      -
> +        name: node-id
> +        type: u32
> +        doc: Node ID targeted by this operation.
> +      -
> +        name: error-id
> +        type: u32
> +        doc: Unique identifier for a specific error within the node.
> +      -
> +        name: error-name
> +        type: string
> +        doc: Name of the error.
> +      -
> +        name: error-threshold
> +        type: u32
> +        doc: Threshold value of the error.
>   
>   operations:
>     list:
> @@ -113,3 +132,21 @@ operations:
>               - node-id
>           reply:
>             attributes: *errorinfo
> +    -
> +      name: get-error-threshold
> +      doc: >-
> +           Retrieve threshold value of the error.
> +           The response includes the id, the name, and current threshold
> +           value of the error.
> +      attribute-set: error-threshold-attrs
> +      flags: [admin-perm]
> +      do:
> +        request:
> +          attributes:
> +            - node-id
> +            - error-id
> +        reply:
> +          attributes:
> +            - error-id
> +            - error-name
> +            - error-threshold
> diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
> index 1f7435d60f11..d2d853d5d69c 100644
> --- a/drivers/gpu/drm/drm_ras.c
> +++ b/drivers/gpu/drm/drm_ras.c
> @@ -37,6 +37,10 @@
>    *    Returns all counters of a node if only Node ID is provided or specific
>    *    error counters.
>    *
> + * 3. GET_ERROR_THRESHOLD: Query threshold value of the error.
> + *    Userspace must provide Node ID and Error ID.
> + *    Returns the threshold value of a specific error.
> + *
>    * Node registration:
>    *
>    * - drm_ras_node_register(): Registers a new node and assigns
> @@ -66,6 +70,8 @@
>    *   operation, fetching all counters from a specific node.
>    * - drm_ras_nl_get_error_counter_doit(): Implements the GET_ERROR_COUNTER doit
>    *   operation, fetching a counter value from a specific node.
> + * - drm_ras_nl_get_error_threshold_doit(): Implements the GET_ERROR_THRESHOLD doit
> + *   operation, fetching the threshold value of a specific error.
>    */
>   
>   static DEFINE_XARRAY_ALLOC(drm_ras_xa);
> @@ -162,6 +168,22 @@ static int get_node_error_counter(u32 node_id, u32 error_id,
>   	return node->query_error_counter(node, error_id, name, value);
>   }
>   
> +static int get_node_error_threshold(u32 node_id, u32 error_id,
> +				    const char **name, u32 *value)
> +{
> +	struct drm_ras_node *node;
> +
> +	node = xa_load(&drm_ras_xa, node_id);
> +	if (!node || !node->query_error_threshold)
> +		return -ENOENT;

For the absence of the function, return -EOPNOTSUPP

> +
> +	if (error_id < node->error_counter_range.first ||
> +	    error_id > node->error_counter_range.last)
> +		return -EINVAL;
> +
> +	return node->query_error_threshold(node, error_id, name, value);
> +}
> +
>   static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
>   				   const char *error_name, u32 value)
>   {
> @@ -180,6 +202,24 @@ static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
>   			   value);
>   }
>   
> +static int msg_reply_threshold_value(struct sk_buff *msg, u32 error_id,
> +				     const char *error_name, u32 value)
> +{
> +	int ret;
> +
> +	ret = nla_put_u32(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID, error_id);
> +	if (ret)
> +		return ret;
> +
> +	ret = nla_put_string(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_NAME,
> +			     error_name);
> +	if (ret)
> +		return ret;
> +
> +	return nla_put_u32(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD,
> +			   value);
> +}
> +
>   static int doit_reply_counter_value(struct genl_info *info, u32 node_id,
>   				    u32 error_id)
>   {
> @@ -216,6 +256,42 @@ static int doit_reply_counter_value(struct genl_info *info, u32 node_id,
>   	return genlmsg_reply(msg, info);
>   }
>   
> +static int doit_reply_threshold_value(struct genl_info *info, u32 node_id,
> +				      u32 error_id)
> +{
> +	struct sk_buff *msg;
> +	struct nlattr *hdr;
> +	const char *error_name;
> +	u32 value;
> +	int ret;
> +
> +	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
> +	if (!msg)
> +		return -ENOMEM;
> +
> +	hdr = genlmsg_iput(msg, info);
> +	if (!hdr) {
> +		nlmsg_free(msg);
> +		return -EMSGSIZE;
> +	}
> +
> +	ret = get_node_error_threshold(node_id, error_id,
> +				       &error_name, &value);
> +	if (ret)
> +		return ret;

You have to cancel and free genlmsg here.
Looks like the counter patch also has the same issue. Will send out a fix.

> +
> +	ret = msg_reply_threshold_value(msg, error_id, error_name, value);
> +	if (ret) {
> +		genlmsg_cancel(msg, hdr);
> +		nlmsg_free(msg);
> +		return ret;
> +	}
> +
> +	genlmsg_end(msg, hdr);
> +
> +	return genlmsg_reply(msg, info);
> +}
> +
>   /**
>    * drm_ras_nl_get_error_counter_dumpit() - Dump all Error Counters
>    * @skb: Netlink message buffer
> @@ -314,6 +390,33 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
>   	return doit_reply_counter_value(info, node_id, error_id);
>   }
>   
> +/**
> + * drm_ras_nl_get_error_threshold_doit() - Query threshold value of the error
Nit: an

Thanks
Riana
> + * @skb: Netlink message buffer
> + * @info: Generic Netlink info containing attributes of the request
> + *
> + * Extracts the node ID and error ID from the netlink attributes and
> + * retrieves the current threshold of the corresponding error. Sends the
> + * result back to the requesting user via the standard Genl reply.
> + *
> + * Return: 0 on success, or negative errno on failure.
> + */
> +int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
> +				      struct genl_info *info)
> +{
> +	u32 node_id, error_id;
> +
> +	if (!info->attrs ||
> +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID) ||
> +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID))
> +		return -EINVAL;
> +
> +	node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID]);
> +	error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID]);
> +
> +	return doit_reply_threshold_value(info, node_id, error_id);
> +}
> +
>   /**
>    * drm_ras_node_register() - Register a new RAS node
>    * @node: Node structure to register
> diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c
> index 16803d0c4a44..48e231734f4d 100644
> --- a/drivers/gpu/drm/drm_ras_nl.c
> +++ b/drivers/gpu/drm/drm_ras_nl.c
> @@ -22,6 +22,12 @@ static const struct nla_policy drm_ras_get_error_counter_dump_nl_policy[DRM_RAS_
>   	[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID] = { .type = NLA_U32, },
>   };
>   
> +/* DRM_RAS_CMD_GET_ERROR_THRESHOLD - do */
> +static const struct nla_policy drm_ras_get_error_threshold_nl_policy[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID + 1] = {
> +	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID] = { .type = NLA_U32, },
> +	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID] = { .type = NLA_U32, },
> +};
> +
>   /* Ops table for drm_ras */
>   static const struct genl_split_ops drm_ras_nl_ops[] = {
>   	{
> @@ -43,6 +49,13 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
>   		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID,
>   		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
>   	},
> +	{
> +		.cmd		= DRM_RAS_CMD_GET_ERROR_THRESHOLD,
> +		.doit		= drm_ras_nl_get_error_threshold_doit,
> +		.policy		= drm_ras_get_error_threshold_nl_policy,
> +		.maxattr	= DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID,
> +		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
> +	},
>   };
>   
>   struct genl_family drm_ras_nl_family __ro_after_init = {
> diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h
> index 06ccd9342773..540fe22e2312 100644
> --- a/drivers/gpu/drm/drm_ras_nl.h
> +++ b/drivers/gpu/drm/drm_ras_nl.h
> @@ -18,6 +18,8 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
>   				      struct genl_info *info);
>   int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
>   					struct netlink_callback *cb);
> +int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
> +					struct genl_info *info);
>   
>   extern struct genl_family drm_ras_nl_family;
>   
> diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
> index 5d50209e51db..50cee70bd065 100644
> --- a/include/drm/drm_ras.h
> +++ b/include/drm/drm_ras.h
> @@ -57,6 +57,20 @@ struct drm_ras_node {
>   	 */
>   	int (*query_error_counter)(struct drm_ras_node *node, u32 error_id,
>   				   const char **name, u32 *val);
> +	/**
> +	 * @query_error_threshold:
> +	 *
> +	 * This callback is used by drm-ras to query threshold value of a
> +	 * specific error.
> +	 *
> +	 * Driver should expect query_error_threshold() to be called with
> +	 * error_id from `error_counter_range.first` to
> +	 * `error_counter_range.last`.
> +	 *
> +	 * Returns: 0 on success, negative error code on failure.
> +	 */
> +	int (*query_error_threshold)(struct drm_ras_node *node, u32 error_id,
> +				     const char **name, u32 *val);
>   
>   	/** @priv: Driver private data */
>   	void *priv;
> diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
> index 5f40fa5b869d..49c5ca497d73 100644
> --- a/include/uapi/drm/drm_ras.h
> +++ b/include/uapi/drm/drm_ras.h
> @@ -38,9 +38,20 @@ enum {
>   	DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1)
>   };
>   
> +enum {
> +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID = 1,
> +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID,
> +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_NAME,
> +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD,
> +
> +	__DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX,
> +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX = (__DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX - 1)
> +};
> +
>   enum {
>   	DRM_RAS_CMD_LIST_NODES = 1,
>   	DRM_RAS_CMD_GET_ERROR_COUNTER,
> +	DRM_RAS_CMD_GET_ERROR_THRESHOLD,
>   
>   	__DRM_RAS_CMD_MAX,
>   	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)

Re: [PATCH v1 05/11] drm/xe/sysctrl: Add system controller interrupt handler

[Tauro, Riana]

On 4/18/2026 2:46 AM, Raag Jadav wrote:
> Add system controller interrupt handler which is denoted by 11th bit in
> GFX master interrupt register. While at it, add worker for scheduling
> system controller work.

Why do we need this series in the threshold patch. From what i see, we 
need only structures
Can't we only redefine those here?

I know you will have to rebase again once any patch is merged. But this 
is unnecessary noise
for the drm patch.

Thanks
Riana

>
> Co-developed-by: Soham Purkait <soham.purkait@intel.com>
> Signed-off-by: Soham Purkait <soham.purkait@intel.com>
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> Reviewed-by: Riana Tauro <riana.tauro@intel.com>
> ---
>   drivers/gpu/drm/xe/regs/xe_irq_regs.h |  1 +
>   drivers/gpu/drm/xe/xe_irq.c           |  2 ++
>   drivers/gpu/drm/xe/xe_sysctrl.c       | 35 +++++++++++++++++++++------
>   drivers/gpu/drm/xe/xe_sysctrl.h       |  1 +
>   drivers/gpu/drm/xe/xe_sysctrl_types.h |  4 +++
>   5 files changed, 36 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/gpu/drm/xe/regs/xe_irq_regs.h b/drivers/gpu/drm/xe/regs/xe_irq_regs.h
> index 9d74f454d3ff..1d6b976c4de0 100644
> --- a/drivers/gpu/drm/xe/regs/xe_irq_regs.h
> +++ b/drivers/gpu/drm/xe/regs/xe_irq_regs.h
> @@ -22,6 +22,7 @@
>   #define   DISPLAY_IRQ				REG_BIT(16)
>   #define   SOC_H2DMEMINT_IRQ			REG_BIT(13)
>   #define   I2C_IRQ				REG_BIT(12)
> +#define   SYSCTRL_IRQ				REG_BIT(11)
>   #define   GT_DW_IRQ(x)				REG_BIT(x)
>   
>   /*
> diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
> index 9a775c6588dc..e9f0b3cad06d 100644
> --- a/drivers/gpu/drm/xe/xe_irq.c
> +++ b/drivers/gpu/drm/xe/xe_irq.c
> @@ -24,6 +24,7 @@
>   #include "xe_mmio.h"
>   #include "xe_pxp.h"
>   #include "xe_sriov.h"
> +#include "xe_sysctrl.h"
>   #include "xe_tile.h"
>   
>   /*
> @@ -525,6 +526,7 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg)
>   				xe_heci_csc_irq_handler(xe, master_ctl);
>   			xe_display_irq_handler(xe, master_ctl);
>   			xe_i2c_irq_handler(xe, master_ctl);
> +			xe_sysctrl_irq_handler(xe, master_ctl);
>   			xe_mert_irq_handler(xe, master_ctl);
>   			gu_misc_iir = gu_misc_irq_ack(xe, master_ctl);
>   		}
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl.c b/drivers/gpu/drm/xe/xe_sysctrl.c
> index 2bcef304eb9a..7de3e73bd8e0 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl.c
> +++ b/drivers/gpu/drm/xe/xe_sysctrl.c
> @@ -8,6 +8,7 @@
>   
>   #include <drm/drm_managed.h>
>   
> +#include "regs/xe_irq_regs.h"
>   #include "regs/xe_sysctrl_regs.h"
>   #include "xe_device.h"
>   #include "xe_mmio.h"
> @@ -30,10 +31,16 @@
>   static void sysctrl_fini(void *arg)
>   {
>   	struct xe_device *xe = arg;
> +	struct xe_sysctrl *sc = &xe->sc;
>   
> +	disable_work_sync(&sc->work);
>   	xe->soc_remapper.set_sysctrl_region(xe, 0);
>   }
>   
> +static void xe_sysctrl_work(struct work_struct *work)
> +{
> +}
> +
>   /**
>    * xe_sysctrl_init() - Initialize System Controller subsystem
>    * @xe: xe device instance
> @@ -55,12 +62,6 @@ int xe_sysctrl_init(struct xe_device *xe)
>   	if (!xe->info.has_sysctrl)
>   		return 0;
>   
> -	xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX);
> -
> -	ret = devm_add_action_or_reset(xe->drm.dev, sysctrl_fini, xe);
> -	if (ret)
> -		return ret;
> -
>   	sc->mmio = devm_kzalloc(xe->drm.dev, sizeof(*sc->mmio), GFP_KERNEL);
>   	if (!sc->mmio)
>   		return -ENOMEM;
> @@ -73,9 +74,29 @@ int xe_sysctrl_init(struct xe_device *xe)
>   	if (ret)
>   		return ret;
>   
> +	xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX);
>   	xe_sysctrl_mailbox_init(sc);
> +	INIT_WORK(&sc->work, xe_sysctrl_work);
>   
> -	return 0;
> +	return devm_add_action_or_reset(xe->drm.dev, sysctrl_fini, xe);
> +}
> +
> +/**
> + * xe_sysctrl_irq_handler() - Handler for System Controller interrupts
> + * @xe: xe device instance
> + * @master_ctl: interrupt register
> + *
> + * Handle interrupts generated by System Controller.
> + */
> +void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl)
> +{
> +	struct xe_sysctrl *sc = &xe->sc;
> +
> +	if (!xe->info.has_sysctrl || !sc->work.func)
> +		return;
> +
> +	if (master_ctl & SYSCTRL_IRQ)
> +		schedule_work(&sc->work);
>   }
>   
>   /**
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl.h b/drivers/gpu/drm/xe/xe_sysctrl.h
> index f3b0f3716b2f..f7469bfc9324 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl.h
> +++ b/drivers/gpu/drm/xe/xe_sysctrl.h
> @@ -17,6 +17,7 @@ static inline struct xe_device *sc_to_xe(struct xe_sysctrl *sc)
>   }
>   
>   int xe_sysctrl_init(struct xe_device *xe);
> +void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl);
>   void xe_sysctrl_pm_resume(struct xe_device *xe);
>   
>   #endif
> diff --git a/drivers/gpu/drm/xe/xe_sysctrl_types.h b/drivers/gpu/drm/xe/xe_sysctrl_types.h
> index 8217f6befe70..5f408d6491ef 100644
> --- a/drivers/gpu/drm/xe/xe_sysctrl_types.h
> +++ b/drivers/gpu/drm/xe/xe_sysctrl_types.h
> @@ -8,6 +8,7 @@
>   
>   #include <linux/mutex.h>
>   #include <linux/types.h>
> +#include <linux/workqueue_types.h>
>   
>   struct xe_mmio;
>   
> @@ -27,6 +28,9 @@ struct xe_sysctrl {
>   
>   	/** @phase_bit: Message boundary phase toggle bit (0 or 1) */
>   	bool phase_bit;
> +
> +	/** @work: Pending events worker */
> +	struct work_struct work;
>   };
>   
>   #endif

Re: [PATCH v1 03/11] drm/ras: Introduce set-error-threshold

[Tauro, Riana]

On 4/18/2026 2:46 AM, Raag Jadav wrote:
> Add set-error-threshold command support which allows setting threshold
> value of the error. Threshold in RAS context means the number of errors
> the hardware is expected to accumulate before it raises them to software.
> This is to have a fine grained control over error notifications that are
> raised by the hardware.
>
> Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> ---
>   Documentation/gpu/drm-ras.rst            |  9 +++++
>   Documentation/netlink/specs/drm_ras.yaml | 12 ++++++
>   drivers/gpu/drm/drm_ras.c                | 48 ++++++++++++++++++++++++
>   drivers/gpu/drm/drm_ras_nl.c             | 14 +++++++
>   drivers/gpu/drm/drm_ras_nl.h             |  2 +
>   include/drm/drm_ras.h                    | 13 +++++++
>   include/uapi/drm/drm_ras.h               |  1 +
>   7 files changed, 99 insertions(+)
>
> diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
> index 6443dfd1677f..a819aa150604 100644
> --- a/Documentation/gpu/drm-ras.rst
> +++ b/Documentation/gpu/drm-ras.rst
> @@ -54,6 +54,8 @@ User space tools can:
>     ``node-id`` and ``error-id`` as parameters.
>   * Query specific error threshold value with the ``get-error-threshold`` command, using both
>     ``node-id`` and ``error-id`` as parameters.
> +* Set specific error threshold value with the ``set-error-threshold`` command, using
> +  ``node-id``, ``error-id`` and ``error-threshold`` as parameters.
>   
>   YAML-based Interface
>   --------------------
> @@ -109,3 +111,10 @@ Example: Query threshold value of a given error
>   
>       sudo ynl --family drm_ras --do get-error-threshold --json '{"node-id":0, "error-id":1}'
>       {'error-id': 1, 'error-name': 'error_name1', 'error-threshold': 0}
> +
> +Example: Set threshold value of a given error
> +
> +.. code-block:: bash
> +
> +    sudo ynl --family drm_ras --do set-error-threshold --json '{"node-id":0, "error-id":1, "error-threshold":8}'
> +    None
> diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
> index 95a939fb987d..09824309cdff 100644
> --- a/Documentation/netlink/specs/drm_ras.yaml
> +++ b/Documentation/netlink/specs/drm_ras.yaml
> @@ -150,3 +150,15 @@ operations:
>               - error-id
>               - error-name
>               - error-threshold
> +    -
> +      name: set-error-threshold
> +      doc: >-
> +           Set threshold value of the error.
> +      attribute-set: error-threshold-attrs
> +      flags: [admin-perm]
> +      do:
> +        request:
> +          attributes:
> +            - node-id
> +            - error-id
> +            - error-threshold
> diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
> index d2d853d5d69c..e4ff6d87f824 100644
> --- a/drivers/gpu/drm/drm_ras.c
> +++ b/drivers/gpu/drm/drm_ras.c
> @@ -41,6 +41,9 @@
>    *    Userspace must provide Node ID and Error ID.
>    *    Returns the threshold value of a specific error.
>    *
> + * 4. SET_ERROR_THRESHOLD: Set threshold value of the error.
> + *    Userspace must provide Node ID, Error ID and Threshold value to be set.
> + *
>    * Node registration:
>    *
>    * - drm_ras_node_register(): Registers a new node and assigns
> @@ -72,6 +75,8 @@
>    *   operation, fetching a counter value from a specific node.
>    * - drm_ras_nl_get_error_threshold_doit(): Implements the GET_ERROR_THRESHOLD doit
>    *   operation, fetching the threshold value of a specific error.
> + * - drm_ras_nl_set_error_threshold_doit(): Implements the SET_ERROR_THRESHOLD doit
> + *   operation, setting the threshold value of a specific error.
>    */
>   
>   static DEFINE_XARRAY_ALLOC(drm_ras_xa);
> @@ -184,6 +189,21 @@ static int get_node_error_threshold(u32 node_id, u32 error_id,
>   	return node->query_error_threshold(node, error_id, name, value);
>   }
>   
> +static int set_node_error_threshold(u32 node_id, u32 error_id, u32 value)
> +{
> +	struct drm_ras_node *node;
> +
> +	node = xa_load(&drm_ras_xa, node_id);
> +	if (!node || !node->set_error_threshold)
> +		return -ENOENT;

Use -EOPNOTSUPP for absence of function

> +
> +	if (error_id < node->error_counter_range.first ||
> +	    error_id > node->error_counter_range.last)
> +		return -EINVAL;
> +
> +	return node->set_error_threshold(node, error_id, value);
> +}
> +
>   static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
>   				   const char *error_name, u32 value)
>   {
> @@ -417,6 +437,34 @@ int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
>   	return doit_reply_threshold_value(info, node_id, error_id);
>   }
>   
> +/**
> + * drm_ras_nl_set_error_threshold_doit() - Set threshold value of the error
> + * @skb: Netlink message buffer
> + * @info: Generic Netlink info containing attributes of the request
> + *
> + * Extracts the node ID, error ID and threshold value from the netlink attributes
> + * and sets the threshold of the corresponding error.
> + *
> + * Return: 0 on success, or negative errno on failure.
> + */
> +int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb,
> +				      struct genl_info *info)
> +{
> +	u32 node_id, error_id, value;
> +
> +	if (!info->attrs ||
> +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID) ||
> +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID) ||
> +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD))
> +		return -EINVAL;
> +
> +	node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID]);
> +	error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID]);
> +	value = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD]);

do we need a check for max threshold here? Probably configured by drivers?
Or is it upto the driver to check? If its upto the driver, please add it 
in the document

Thanks
Riana

> +
> +	return set_node_error_threshold(node_id, error_id, value);
> +}
> +
>   /**
>    * drm_ras_node_register() - Register a new RAS node
>    * @node: Node structure to register
> diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c
> index 48e231734f4d..8b202d773dac 100644
> --- a/drivers/gpu/drm/drm_ras_nl.c
> +++ b/drivers/gpu/drm/drm_ras_nl.c
> @@ -28,6 +28,13 @@ static const struct nla_policy drm_ras_get_error_threshold_nl_policy[DRM_RAS_A_E
>   	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID] = { .type = NLA_U32, },
>   };
>   
> +/* DRM_RAS_CMD_SET_ERROR_THRESHOLD - do */
> +static const struct nla_policy drm_ras_set_error_threshold_nl_policy[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD + 1] = {
> +	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID] = { .type = NLA_U32, },
> +	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID] = { .type = NLA_U32, },
> +	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD] = { .type = NLA_U32, },
> +};
> +
>   /* Ops table for drm_ras */
>   static const struct genl_split_ops drm_ras_nl_ops[] = {
>   	{
> @@ -56,6 +63,13 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
>   		.maxattr	= DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID,
>   		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
>   	},
> +	{
> +		.cmd		= DRM_RAS_CMD_SET_ERROR_THRESHOLD,
> +		.doit		= drm_ras_nl_set_error_threshold_doit,
> +		.policy		= drm_ras_set_error_threshold_nl_policy,
> +		.maxattr	= DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD,
> +		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
> +	},
>   };
>   
>   struct genl_family drm_ras_nl_family __ro_after_init = {
> diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h
> index 540fe22e2312..9db7f5d00201 100644
> --- a/drivers/gpu/drm/drm_ras_nl.h
> +++ b/drivers/gpu/drm/drm_ras_nl.h
> @@ -20,6 +20,8 @@ int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
>   					struct netlink_callback *cb);
>   int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
>   					struct genl_info *info);
> +int drm_ras_nl_set_error_threshold_doit(struct sk_buff *skb,
> +					struct genl_info *info);
>   
>   extern struct genl_family drm_ras_nl_family;
>   
> diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
> index 50cee70bd065..7a69821b8b78 100644
> --- a/include/drm/drm_ras.h
> +++ b/include/drm/drm_ras.h
> @@ -71,6 +71,19 @@ struct drm_ras_node {
>   	 */
>   	int (*query_error_threshold)(struct drm_ras_node *node, u32 error_id,
>   				     const char **name, u32 *val);
> +	/**
> +	 * @set_error_threshold:
> +	 *
> +	 * This callback is used by drm-ras to set threshold value of a specific
> +	 * error.
> +	 *
> +	 * Driver should expect set_error_threshold() to be called with error_id
> +	 * from `error_counter_range.first` to `error_counter_range.last`.
> +	 *
> +	 * Returns: 0 on success, negative error code on failure.
> +	 */
> +	int (*set_error_threshold)(struct drm_ras_node *node, u32 error_id,
> +				   u32 val);
>   
>   	/** @priv: Driver private data */
>   	void *priv;
> diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
> index 49c5ca497d73..8ff0311d0d63 100644
> --- a/include/uapi/drm/drm_ras.h
> +++ b/include/uapi/drm/drm_ras.h
> @@ -52,6 +52,7 @@ enum {
>   	DRM_RAS_CMD_LIST_NODES = 1,
>   	DRM_RAS_CMD_GET_ERROR_COUNTER,
>   	DRM_RAS_CMD_GET_ERROR_THRESHOLD,
> +	DRM_RAS_CMD_SET_ERROR_THRESHOLD,
>   
>   	__DRM_RAS_CMD_MAX,
>   	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)

Re: [PATCH v1 02/11] drm/ras: Introduce get-error-threshold

[Raag Jadav]

On Wed, Apr 22, 2026 at 11:19:36AM +0530, Tauro, Riana wrote:
> On 4/18/2026 2:46 AM, Raag Jadav wrote:
> > Add get-error-threshold command support which allows querying threshold
> > value of the error. Threshold in RAS context means the number of errors
> > the hardware is expected to accumulate before it raises them to software.
> > This is to have a fine grained control over error notifications that are
> > raised by the hardware.
> > 
> > Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> > ---
> >   Documentation/gpu/drm-ras.rst            |   8 ++
> >   Documentation/netlink/specs/drm_ras.yaml |  37 ++++++++
> >   drivers/gpu/drm/drm_ras.c                | 103 +++++++++++++++++++++++
> >   drivers/gpu/drm/drm_ras_nl.c             |  13 +++
> >   drivers/gpu/drm/drm_ras_nl.h             |   2 +
> >   include/drm/drm_ras.h                    |  14 +++
> >   include/uapi/drm/drm_ras.h               |  11 +++
> >   7 files changed, 188 insertions(+)
> > 
> > diff --git a/Documentation/gpu/drm-ras.rst b/Documentation/gpu/drm-ras.rst
> > index 70b246a78fc8..6443dfd1677f 100644
> > --- a/Documentation/gpu/drm-ras.rst
> > +++ b/Documentation/gpu/drm-ras.rst
> > @@ -52,6 +52,8 @@ User space tools can:
> >     as a parameter.
> >   * Query specific error counter values with the ``get-error-counter`` command, using both
> >     ``node-id`` and ``error-id`` as parameters.
> > +* Query specific error threshold value with the ``get-error-threshold`` command, using both
> > +  ``node-id`` and ``error-id`` as parameters.
> Also define what is a thresold. How can it be used?

Sure, I'll append commit message description here.

> >   YAML-based Interface
> >   --------------------
> > @@ -101,3 +103,9 @@ Example: Query an error counter for a given node
> >       sudo ynl --family drm_ras --do get-error-counter --json '{"node-id":0, "error-id":1}'
> >       {'error-id': 1, 'error-name': 'error_name1', 'error-value': 0}
> > +Example: Query threshold value of a given error
> > +
> > +.. code-block:: bash
> > +
> > +    sudo ynl --family drm_ras --do get-error-threshold --json '{"node-id":0, "error-id":1}'
> > +    {'error-id': 1, 'error-name': 'error_name1', 'error-threshold': 0}
> > diff --git a/Documentation/netlink/specs/drm_ras.yaml b/Documentation/netlink/specs/drm_ras.yaml
> > index 79af25dac3c5..95a939fb987d 100644
> > --- a/Documentation/netlink/specs/drm_ras.yaml
> > +++ b/Documentation/netlink/specs/drm_ras.yaml
> > @@ -69,6 +69,25 @@ attribute-sets:
> >           name: error-value
> >           type: u32
> >           doc: Current value of the requested error counter.
> > +  -
> > +    name: error-threshold-attrs
> > +    attributes:
> > +      -
> > +        name: node-id
> > +        type: u32
> > +        doc: Node ID targeted by this operation.
> > +      -
> > +        name: error-id
> > +        type: u32
> > +        doc: Unique identifier for a specific error within the node.
> > +      -
> > +        name: error-name
> > +        type: string
> > +        doc: Name of the error.
> > +      -
> > +        name: error-threshold
> > +        type: u32
> > +        doc: Threshold value of the error.
> >   operations:
> >     list:
> > @@ -113,3 +132,21 @@ operations:
> >               - node-id
> >           reply:
> >             attributes: *errorinfo
> > +    -
> > +      name: get-error-threshold
> > +      doc: >-
> > +           Retrieve threshold value of the error.
> > +           The response includes the id, the name, and current threshold
> > +           value of the error.
> > +      attribute-set: error-threshold-attrs
> > +      flags: [admin-perm]
> > +      do:
> > +        request:
> > +          attributes:
> > +            - node-id
> > +            - error-id
> > +        reply:
> > +          attributes:
> > +            - error-id
> > +            - error-name
> > +            - error-threshold
> > diff --git a/drivers/gpu/drm/drm_ras.c b/drivers/gpu/drm/drm_ras.c
> > index 1f7435d60f11..d2d853d5d69c 100644
> > --- a/drivers/gpu/drm/drm_ras.c
> > +++ b/drivers/gpu/drm/drm_ras.c
> > @@ -37,6 +37,10 @@
> >    *    Returns all counters of a node if only Node ID is provided or specific
> >    *    error counters.
> >    *
> > + * 3. GET_ERROR_THRESHOLD: Query threshold value of the error.
> > + *    Userspace must provide Node ID and Error ID.
> > + *    Returns the threshold value of a specific error.
> > + *
> >    * Node registration:
> >    *
> >    * - drm_ras_node_register(): Registers a new node and assigns
> > @@ -66,6 +70,8 @@
> >    *   operation, fetching all counters from a specific node.
> >    * - drm_ras_nl_get_error_counter_doit(): Implements the GET_ERROR_COUNTER doit
> >    *   operation, fetching a counter value from a specific node.
> > + * - drm_ras_nl_get_error_threshold_doit(): Implements the GET_ERROR_THRESHOLD doit
> > + *   operation, fetching the threshold value of a specific error.
> >    */
> >   static DEFINE_XARRAY_ALLOC(drm_ras_xa);
> > @@ -162,6 +168,22 @@ static int get_node_error_counter(u32 node_id, u32 error_id,
> >   	return node->query_error_counter(node, error_id, name, value);
> >   }
> > +static int get_node_error_threshold(u32 node_id, u32 error_id,
> > +				    const char **name, u32 *value)
> > +{
> > +	struct drm_ras_node *node;
> > +
> > +	node = xa_load(&drm_ras_xa, node_id);
> > +	if (!node || !node->query_error_threshold)
> > +		return -ENOENT;
> 
> For the absence of the function, return -EOPNOTSUPP

Works for me, but then it should be consistent for all commands.

> > +
> > +	if (error_id < node->error_counter_range.first ||
> > +	    error_id > node->error_counter_range.last)
> > +		return -EINVAL;
> > +
> > +	return node->query_error_threshold(node, error_id, name, value);
> > +}
> > +
> >   static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
> >   				   const char *error_name, u32 value)
> >   {
> > @@ -180,6 +202,24 @@ static int msg_reply_counter_value(struct sk_buff *msg, u32 error_id,
> >   			   value);
> >   }
> > +static int msg_reply_threshold_value(struct sk_buff *msg, u32 error_id,
> > +				     const char *error_name, u32 value)
> > +{
> > +	int ret;
> > +
> > +	ret = nla_put_u32(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID, error_id);
> > +	if (ret)
> > +		return ret;
> > +
> > +	ret = nla_put_string(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_NAME,
> > +			     error_name);
> > +	if (ret)
> > +		return ret;
> > +
> > +	return nla_put_u32(msg, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD,
> > +			   value);
> > +}
> > +
> >   static int doit_reply_counter_value(struct genl_info *info, u32 node_id,
> >   				    u32 error_id)
> >   {
> > @@ -216,6 +256,42 @@ static int doit_reply_counter_value(struct genl_info *info, u32 node_id,
> >   	return genlmsg_reply(msg, info);
> >   }
> > +static int doit_reply_threshold_value(struct genl_info *info, u32 node_id,
> > +				      u32 error_id)
> > +{
> > +	struct sk_buff *msg;
> > +	struct nlattr *hdr;
> > +	const char *error_name;
> > +	u32 value;
> > +	int ret;
> > +
> > +	msg = genlmsg_new(NLMSG_GOODSIZE, GFP_KERNEL);
> > +	if (!msg)
> > +		return -ENOMEM;
> > +
> > +	hdr = genlmsg_iput(msg, info);
> > +	if (!hdr) {
> > +		nlmsg_free(msg);
> > +		return -EMSGSIZE;
> > +	}
> > +
> > +	ret = get_node_error_threshold(node_id, error_id,
> > +				       &error_name, &value);
> > +	if (ret)
> > +		return ret;
> 
> You have to cancel and free genlmsg here.
> Looks like the counter patch also has the same issue. Will send out a fix.

Yeah, failed attempt at stealing your code :(

Raag

> > +	ret = msg_reply_threshold_value(msg, error_id, error_name, value);
> > +	if (ret) {
> > +		genlmsg_cancel(msg, hdr);
> > +		nlmsg_free(msg);
> > +		return ret;
> > +	}
> > +
> > +	genlmsg_end(msg, hdr);
> > +
> > +	return genlmsg_reply(msg, info);
> > +}
> > +
> >   /**
> >    * drm_ras_nl_get_error_counter_dumpit() - Dump all Error Counters
> >    * @skb: Netlink message buffer
> > @@ -314,6 +390,33 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
> >   	return doit_reply_counter_value(info, node_id, error_id);
> >   }
> > +/**
> > + * drm_ras_nl_get_error_threshold_doit() - Query threshold value of the error
> Nit: an
> 
> Thanks
> Riana
> > + * @skb: Netlink message buffer
> > + * @info: Generic Netlink info containing attributes of the request
> > + *
> > + * Extracts the node ID and error ID from the netlink attributes and
> > + * retrieves the current threshold of the corresponding error. Sends the
> > + * result back to the requesting user via the standard Genl reply.
> > + *
> > + * Return: 0 on success, or negative errno on failure.
> > + */
> > +int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
> > +				      struct genl_info *info)
> > +{
> > +	u32 node_id, error_id;
> > +
> > +	if (!info->attrs ||
> > +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID) ||
> > +	    GENL_REQ_ATTR_CHECK(info, DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID))
> > +		return -EINVAL;
> > +
> > +	node_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID]);
> > +	error_id = nla_get_u32(info->attrs[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID]);
> > +
> > +	return doit_reply_threshold_value(info, node_id, error_id);
> > +}
> > +
> >   /**
> >    * drm_ras_node_register() - Register a new RAS node
> >    * @node: Node structure to register
> > diff --git a/drivers/gpu/drm/drm_ras_nl.c b/drivers/gpu/drm/drm_ras_nl.c
> > index 16803d0c4a44..48e231734f4d 100644
> > --- a/drivers/gpu/drm/drm_ras_nl.c
> > +++ b/drivers/gpu/drm/drm_ras_nl.c
> > @@ -22,6 +22,12 @@ static const struct nla_policy drm_ras_get_error_counter_dump_nl_policy[DRM_RAS_
> >   	[DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID] = { .type = NLA_U32, },
> >   };
> > +/* DRM_RAS_CMD_GET_ERROR_THRESHOLD - do */
> > +static const struct nla_policy drm_ras_get_error_threshold_nl_policy[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID + 1] = {
> > +	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID] = { .type = NLA_U32, },
> > +	[DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID] = { .type = NLA_U32, },
> > +};
> > +
> >   /* Ops table for drm_ras */
> >   static const struct genl_split_ops drm_ras_nl_ops[] = {
> >   	{
> > @@ -43,6 +49,13 @@ static const struct genl_split_ops drm_ras_nl_ops[] = {
> >   		.maxattr	= DRM_RAS_A_ERROR_COUNTER_ATTRS_NODE_ID,
> >   		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DUMP,
> >   	},
> > +	{
> > +		.cmd		= DRM_RAS_CMD_GET_ERROR_THRESHOLD,
> > +		.doit		= drm_ras_nl_get_error_threshold_doit,
> > +		.policy		= drm_ras_get_error_threshold_nl_policy,
> > +		.maxattr	= DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID,
> > +		.flags		= GENL_ADMIN_PERM | GENL_CMD_CAP_DO,
> > +	},
> >   };
> >   struct genl_family drm_ras_nl_family __ro_after_init = {
> > diff --git a/drivers/gpu/drm/drm_ras_nl.h b/drivers/gpu/drm/drm_ras_nl.h
> > index 06ccd9342773..540fe22e2312 100644
> > --- a/drivers/gpu/drm/drm_ras_nl.h
> > +++ b/drivers/gpu/drm/drm_ras_nl.h
> > @@ -18,6 +18,8 @@ int drm_ras_nl_get_error_counter_doit(struct sk_buff *skb,
> >   				      struct genl_info *info);
> >   int drm_ras_nl_get_error_counter_dumpit(struct sk_buff *skb,
> >   					struct netlink_callback *cb);
> > +int drm_ras_nl_get_error_threshold_doit(struct sk_buff *skb,
> > +					struct genl_info *info);
> >   extern struct genl_family drm_ras_nl_family;
> > diff --git a/include/drm/drm_ras.h b/include/drm/drm_ras.h
> > index 5d50209e51db..50cee70bd065 100644
> > --- a/include/drm/drm_ras.h
> > +++ b/include/drm/drm_ras.h
> > @@ -57,6 +57,20 @@ struct drm_ras_node {
> >   	 */
> >   	int (*query_error_counter)(struct drm_ras_node *node, u32 error_id,
> >   				   const char **name, u32 *val);
> > +	/**
> > +	 * @query_error_threshold:
> > +	 *
> > +	 * This callback is used by drm-ras to query threshold value of a
> > +	 * specific error.
> > +	 *
> > +	 * Driver should expect query_error_threshold() to be called with
> > +	 * error_id from `error_counter_range.first` to
> > +	 * `error_counter_range.last`.
> > +	 *
> > +	 * Returns: 0 on success, negative error code on failure.
> > +	 */
> > +	int (*query_error_threshold)(struct drm_ras_node *node, u32 error_id,
> > +				     const char **name, u32 *val);
> >   	/** @priv: Driver private data */
> >   	void *priv;
> > diff --git a/include/uapi/drm/drm_ras.h b/include/uapi/drm/drm_ras.h
> > index 5f40fa5b869d..49c5ca497d73 100644
> > --- a/include/uapi/drm/drm_ras.h
> > +++ b/include/uapi/drm/drm_ras.h
> > @@ -38,9 +38,20 @@ enum {
> >   	DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX = (__DRM_RAS_A_ERROR_COUNTER_ATTRS_MAX - 1)
> >   };
> > +enum {
> > +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_NODE_ID = 1,
> > +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_ID,
> > +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_NAME,
> > +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_ERROR_THRESHOLD,
> > +
> > +	__DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX,
> > +	DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX = (__DRM_RAS_A_ERROR_THRESHOLD_ATTRS_MAX - 1)
> > +};
> > +
> >   enum {
> >   	DRM_RAS_CMD_LIST_NODES = 1,
> >   	DRM_RAS_CMD_GET_ERROR_COUNTER,
> > +	DRM_RAS_CMD_GET_ERROR_THRESHOLD,
> >   	__DRM_RAS_CMD_MAX,
> >   	DRM_RAS_CMD_MAX = (__DRM_RAS_CMD_MAX - 1)

Re: [PATCH v1 05/11] drm/xe/sysctrl: Add system controller interrupt handler

[Raag Jadav]

On Wed, Apr 22, 2026 at 11:25:44AM +0530, Tauro, Riana wrote:
> On 4/18/2026 2:46 AM, Raag Jadav wrote:
> > Add system controller interrupt handler which is denoted by 11th bit in
> > GFX master interrupt register. While at it, add worker for scheduling
> > system controller work.
> 
> Why do we need this series in the threshold patch. From what i see, we need
> only structures
> Can't we only redefine those here?
> 
> I know you will have to rebase again once any patch is merged. But this is
> unnecessary noise
> for the drm patch.

We have threshold crossed event so I thought it was relevant here. We can
merge it independently if you're okay with it.

Raag

> > Co-developed-by: Soham Purkait <soham.purkait@intel.com>
> > Signed-off-by: Soham Purkait <soham.purkait@intel.com>
> > Signed-off-by: Raag Jadav <raag.jadav@intel.com>
> > Reviewed-by: Mallesh Koujalagi <mallesh.koujalagi@intel.com>
> > Reviewed-by: Riana Tauro <riana.tauro@intel.com>
> > ---
> >   drivers/gpu/drm/xe/regs/xe_irq_regs.h |  1 +
> >   drivers/gpu/drm/xe/xe_irq.c           |  2 ++
> >   drivers/gpu/drm/xe/xe_sysctrl.c       | 35 +++++++++++++++++++++------
> >   drivers/gpu/drm/xe/xe_sysctrl.h       |  1 +
> >   drivers/gpu/drm/xe/xe_sysctrl_types.h |  4 +++
> >   5 files changed, 36 insertions(+), 7 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/xe/regs/xe_irq_regs.h b/drivers/gpu/drm/xe/regs/xe_irq_regs.h
> > index 9d74f454d3ff..1d6b976c4de0 100644
> > --- a/drivers/gpu/drm/xe/regs/xe_irq_regs.h
> > +++ b/drivers/gpu/drm/xe/regs/xe_irq_regs.h
> > @@ -22,6 +22,7 @@
> >   #define   DISPLAY_IRQ				REG_BIT(16)
> >   #define   SOC_H2DMEMINT_IRQ			REG_BIT(13)
> >   #define   I2C_IRQ				REG_BIT(12)
> > +#define   SYSCTRL_IRQ				REG_BIT(11)
> >   #define   GT_DW_IRQ(x)				REG_BIT(x)
> >   /*
> > diff --git a/drivers/gpu/drm/xe/xe_irq.c b/drivers/gpu/drm/xe/xe_irq.c
> > index 9a775c6588dc..e9f0b3cad06d 100644
> > --- a/drivers/gpu/drm/xe/xe_irq.c
> > +++ b/drivers/gpu/drm/xe/xe_irq.c
> > @@ -24,6 +24,7 @@
> >   #include "xe_mmio.h"
> >   #include "xe_pxp.h"
> >   #include "xe_sriov.h"
> > +#include "xe_sysctrl.h"
> >   #include "xe_tile.h"
> >   /*
> > @@ -525,6 +526,7 @@ static irqreturn_t dg1_irq_handler(int irq, void *arg)
> >   				xe_heci_csc_irq_handler(xe, master_ctl);
> >   			xe_display_irq_handler(xe, master_ctl);
> >   			xe_i2c_irq_handler(xe, master_ctl);
> > +			xe_sysctrl_irq_handler(xe, master_ctl);
> >   			xe_mert_irq_handler(xe, master_ctl);
> >   			gu_misc_iir = gu_misc_irq_ack(xe, master_ctl);
> >   		}
> > diff --git a/drivers/gpu/drm/xe/xe_sysctrl.c b/drivers/gpu/drm/xe/xe_sysctrl.c
> > index 2bcef304eb9a..7de3e73bd8e0 100644
> > --- a/drivers/gpu/drm/xe/xe_sysctrl.c
> > +++ b/drivers/gpu/drm/xe/xe_sysctrl.c
> > @@ -8,6 +8,7 @@
> >   #include <drm/drm_managed.h>
> > +#include "regs/xe_irq_regs.h"
> >   #include "regs/xe_sysctrl_regs.h"
> >   #include "xe_device.h"
> >   #include "xe_mmio.h"
> > @@ -30,10 +31,16 @@
> >   static void sysctrl_fini(void *arg)
> >   {
> >   	struct xe_device *xe = arg;
> > +	struct xe_sysctrl *sc = &xe->sc;
> > +	disable_work_sync(&sc->work);
> >   	xe->soc_remapper.set_sysctrl_region(xe, 0);
> >   }
> > +static void xe_sysctrl_work(struct work_struct *work)
> > +{
> > +}
> > +
> >   /**
> >    * xe_sysctrl_init() - Initialize System Controller subsystem
> >    * @xe: xe device instance
> > @@ -55,12 +62,6 @@ int xe_sysctrl_init(struct xe_device *xe)
> >   	if (!xe->info.has_sysctrl)
> >   		return 0;
> > -	xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX);
> > -
> > -	ret = devm_add_action_or_reset(xe->drm.dev, sysctrl_fini, xe);
> > -	if (ret)
> > -		return ret;
> > -
> >   	sc->mmio = devm_kzalloc(xe->drm.dev, sizeof(*sc->mmio), GFP_KERNEL);
> >   	if (!sc->mmio)
> >   		return -ENOMEM;
> > @@ -73,9 +74,29 @@ int xe_sysctrl_init(struct xe_device *xe)
> >   	if (ret)
> >   		return ret;
> > +	xe->soc_remapper.set_sysctrl_region(xe, SYSCTRL_MAILBOX_INDEX);
> >   	xe_sysctrl_mailbox_init(sc);
> > +	INIT_WORK(&sc->work, xe_sysctrl_work);
> > -	return 0;
> > +	return devm_add_action_or_reset(xe->drm.dev, sysctrl_fini, xe);
> > +}
> > +
> > +/**
> > + * xe_sysctrl_irq_handler() - Handler for System Controller interrupts
> > + * @xe: xe device instance
> > + * @master_ctl: interrupt register
> > + *
> > + * Handle interrupts generated by System Controller.
> > + */
> > +void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl)
> > +{
> > +	struct xe_sysctrl *sc = &xe->sc;
> > +
> > +	if (!xe->info.has_sysctrl || !sc->work.func)
> > +		return;
> > +
> > +	if (master_ctl & SYSCTRL_IRQ)
> > +		schedule_work(&sc->work);
> >   }
> >   /**
> > diff --git a/drivers/gpu/drm/xe/xe_sysctrl.h b/drivers/gpu/drm/xe/xe_sysctrl.h
> > index f3b0f3716b2f..f7469bfc9324 100644
> > --- a/drivers/gpu/drm/xe/xe_sysctrl.h
> > +++ b/drivers/gpu/drm/xe/xe_sysctrl.h
> > @@ -17,6 +17,7 @@ static inline struct xe_device *sc_to_xe(struct xe_sysctrl *sc)
> >   }
> >   int xe_sysctrl_init(struct xe_device *xe);
> > +void xe_sysctrl_irq_handler(struct xe_device *xe, u32 master_ctl);
> >   void xe_sysctrl_pm_resume(struct xe_device *xe);
> >   #endif
> > diff --git a/drivers/gpu/drm/xe/xe_sysctrl_types.h b/drivers/gpu/drm/xe/xe_sysctrl_types.h
> > index 8217f6befe70..5f408d6491ef 100644
> > --- a/drivers/gpu/drm/xe/xe_sysctrl_types.h
> > +++ b/drivers/gpu/drm/xe/xe_sysctrl_types.h
> > @@ -8,6 +8,7 @@
> >   #include <linux/mutex.h>
> >   #include <linux/types.h>
> > +#include <linux/workqueue_types.h>
> >   struct xe_mmio;
> > @@ -27,6 +28,9 @@ struct xe_sysctrl {
> >   	/** @phase_bit: Message boundary phase toggle bit (0 or 1) */
> >   	bool phase_bit;
> > +
> > +	/** @work: Pending events worker */
> > +	struct work_struct work;
> >   };
> >   #endif